<?xml version="1.0" encoding="UTF-8"?><rss xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:atom="http://www.w3.org/2005/Atom" version="2.0" xmlns:cc="http://cyber.law.harvard.edu/rss/creativeCommonsRssModule.html">
    <channel>
        <title><![CDATA[Stories by Katherine Lordi on Medium]]></title>
        <description><![CDATA[Stories by Katherine Lordi on Medium]]></description>
        <link>https://medium.com/@klordihavemercy?source=rss-1f00722da339------2</link>
        <image>
            <url>https://cdn-images-1.medium.com/fit/c/150/150/1*qnQwsl0Rcvr-MttvqpWA6w@2x.jpeg</url>
            <title>Stories by Katherine Lordi on Medium</title>
            <link>https://medium.com/@klordihavemercy?source=rss-1f00722da339------2</link>
        </image>
        <generator>Medium</generator>
        <lastBuildDate>Sat, 21 Nov 2026 01:21:51 GMT</lastBuildDate>
        <atom:link href="https://medium.com/@klordihavemercy/feed" rel="self" type="application/rss+xml"/>
        <webMaster><![CDATA[yourfriends@medium.com]]></webMaster>
        <atom:link href="http://medium.superfeedr.com/" rel="hub"/>
        <item>
            <title><![CDATA[Intro to @klordihavemercy]]></title>
            <link>https://klordihavemercy.medium.com/intro-to-klordihavemercy-7039e440be84?source=rss-1f00722da339------2</link>
            <guid isPermaLink="false">https://medium.com/p/7039e440be84</guid>
            <category><![CDATA[hyrox]]></category>
            <category><![CDATA[fitness-tips]]></category>
            <category><![CDATA[fitness]]></category>
            <category><![CDATA[product-management]]></category>
            <dc:creator><![CDATA[Katherine Lordi]]></dc:creator>
            <pubDate>Tue, 24 Feb 2026 18:04:16 GMT</pubDate>
            <atom:updated>2026-02-24T18:04:16.713Z</atom:updated>
            <content:encoded><![CDATA[<p>Welcome to @klordihavemercy, a Substack where I share my learning and growth across my career and fitness pursuits: Product Management, Fitness Coaching, and Race Training.</p><p><em>NOTE: I’ll share content across both Medium &amp; Substack! Sorry if I say “Substack”.</em></p><h3>What I do [ ]</h3><p>Hi! 👋🏼 My name is Katherine (aka klordi), and I am a <strong>full-time Product Manager by day and a part-time functional fitness coach</strong> by morning / evening. I like to wear a few hats if I can!</p><h4>[ PM ]</h4><p><strong>As a product manager in a global organization</strong>, I’m striving to broaden my influence and rebuild some technical, hands‑on skills that I’ve lost over the years. I’m continuing to grow in PM fundamentals — data‑driven decision‑making, user empathy, product strategy, cross-functional alignment, and full project delivery — while also becoming a stronger mentor for others in product management and related fields.</p><p><em>NOTE: ClaudeAI helped me clean up that one </em>😊</p><p><strong><em>Objectives:</em></strong><em> Grind well 9–5, continue online education, and be hands-on with personal side projects</em></p><h4>[ Functional Fitness Coach! ]</h4><p><strong>As a functional fitness coach,</strong> my mission is to build an uplifting community, coach movement fundamentals with intention, and help members load and push intensity safely. I lead with a quality‑over‑quantity mindset and want to make lifting and training hard something to genuinely look forward to 😉😊.</p><p><strong><em>Objectives:</em></strong><em> Continuing education to grow as both a group fitness coach and 1:1 certified personal trainer</em></p><h4>[ Race Training for HYROX! ]</h4><p><strong>Outside of work but fueled by my love for functional fitness,</strong> I am <strong>currently training for </strong><a href="https://hyrox.com/the-fitness-race/"><strong>HYROX</strong></a><strong> races.</strong> I have a running and lifting background and have trained for half + full marathons, but I love how HYROX combines both in a way that feels challenging and accessible to train for in a standard gym. I also love the HYROX community.</p><p>I also love how this race <strong>requires me to get good and efficient at different functional exercises</strong>. For example, an athlete can be a beast in station #1: SkiErg (my personal weakness) but not as great in Station #7: Walking Lunges (my personal strength). Training becomes a mix of pacing, efficiency, technique, and knowing when to push or hold back.</p><p><strong><em>Goal:</em></strong><em> BET ON MYSELF. PR solos and doubles races this upcoming race season.</em></p><p><strong><em>Broad Objective:</em></strong><em> Train intentionally to become a well‑rounded athlete — while still honoring my aesthetic goals — with a targeted focus on improving key HYROX stations: race‑pace running, SkiErg, sled pull, burpee broad jumps, and wall balls.</em></p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/0*xmGbqZTZXu5oYN0s.png" /><figcaption>Hyrox Boston Open Solos 2025</figcaption></figure><h4>[ F.I.R.S.T. Robotics Volunteer ]</h4><p><strong>As a volunteer with </strong><a href="https://www.firstinspires.org/community/volunteers"><strong>FIRST Robotics</strong></a><strong> during competition season, </strong>my goal is to give back to the organization that has given me so much and helped lead me to being a Product Manager. In this program, teams of students learn from mentors to build robots to complete a sports-like challenge! However, FIRST is also <em>“more than robots”</em> because it helps students build real-world skills, confidence, and instills a love of creative problem‑solving, all while having a blast.</p><p><strong><em>Goal:</em></strong><em> Become a larger advocate and voice for FIRST in my company and beyond to help empower the next generation of STEM leaders.</em></p><figure><img alt="" src="https://cdn-images-1.medium.com/max/960/0*0O0r4ZvYS5Y-2khh.jpeg" /><figcaption>My high school robotics days! ~2012–13. This robot was designed to throw frisbees.</figcaption></figure><h3>Why I am starting this</h3><p>I’ve learned that I care more about being <strong>ambitious in the journey</strong> than ambitious in chasing a specific end result.</p><p>I’m excited write on Substack to:</p><ul><li>Share the <strong>problems I’m solving and the actions I’m taking</strong></li><li>Highlight <strong>what I’m learning</strong> along the way</li><li>Showcase <strong>what I’m building and the tools I’m using</strong> (and how I use them)</li><li>Share my <strong>race training journey and milestones</strong> (e.g. <strong>HYROX</strong> right now!)</li><li>Reflect on my <strong>experiences</strong> as I pursue the ambitions I mentioned above</li></ul><h3>See ya later!!</h3><p>If any of this sounds interesting, I hope you’ll stick around for more — just hit subscribe!! And if you want to connect, swap ideas, or geek out about PM or fitness, please message me.</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=7039e440be84" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[The Financial Literacy Gender Gap & Deeper Dive on Ellevest.]]></title>
            <link>https://klordihavemercy.medium.com/the-financial-literacy-gender-gap-deeper-dive-on-ellevest-4859f466d253?source=rss-1f00722da339------2</link>
            <guid isPermaLink="false">https://medium.com/p/4859f466d253</guid>
            <category><![CDATA[competition]]></category>
            <category><![CDATA[personal-finance]]></category>
            <category><![CDATA[investing]]></category>
            <category><![CDATA[financial-literacy]]></category>
            <category><![CDATA[women]]></category>
            <dc:creator><![CDATA[Katherine Lordi]]></dc:creator>
            <pubDate>Tue, 26 Oct 2021 09:08:40 GMT</pubDate>
            <atom:updated>2021-11-02T01:49:31.228Z</atom:updated>
            <content:encoded><![CDATA[<h4>The financial industry wasn’t built for women, but Ellevest was. Here’s a look at Ellevest’s disruptive technology through Porter’s 5 Forces.</h4><h3>Intro — Financial Literacy, Men, Women &amp; Building Confidence</h3><p>Ever question your skills and abilities or if you’re good enough at something? <em>*Raises hand*</em>. It’s normal to feel this way, and often, these feelings arise due to a lack of confidence in ourselves. Therefore, practice makes perfect! Thinking about confidence in the realm of financial literacy:</p><blockquote><em>‘Women have lower financial literacy than men, but they know more than they think they know.’</em><strong><em> </em></strong>(<a href="https://www.nber.org/system/files/working_papers/w28207/w28207.pdf?utm_campaign=PANTHEON_STRIPPED&amp;%3Butm_medium=PANTHEON_STRIPPED&amp;%3Butm_source=PANTHEON_STRIPPED"><em>Financial Fragility During the Covid-19 Pandemic</em></a>)</blockquote><p>A couple of weeks ago, I hit you with some<a href="https://k-lordi.medium.com/financial-literacy-the-role-of-the-news-media-industry-f98f73b78765"> stats</a> related to financial literacy as a whole. Now, here is one related to the <strong>male-female financial literacy gap</strong> reported by <a href="https://www.marketwatch.com/story/whats-behind-the-financial-literacy-gender-gap-these-academics-both-male-and-female-found-one-answer-11620068977">MarketWatch</a> according to a <a href="https://www.nber.org/system/files/working_papers/w28207/w28207.pdf?utm_campaign=PANTHEON_STRIPPED&amp;%3Butm_medium=PANTHEON_STRIPPED&amp;%3Butm_source=PANTHEON_STRIPPED">financal literacy survey</a> conducted during the pandemic in 2020. This research reveals that there is a link between financial literacy and financial resilience to make important life decisions and achieve various life goals such as saving for education and retirement, raising a family, and running a business.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/640/0*iTSchVD3znJKXfv7" /><figcaption>From<a href="https://www.annuity.org/financial-literacy/women/"> https://www.annuity.org/financial-literacy/women/</a>.</figcaption></figure><p>The research suggests that <strong>1/3 of the financial literacy gender gap can be explained by lower confidence levels among women</strong>. For example, when asked about if they know the concept of risk diversification, 55% of women indicated that they do not know compared to 30% of men, revealing a 25% gap. However, when asked an actual question about risk diversification, some 82% of men answered correctly compared to some 73% of women, which is only a 9% gap. From the study, researchers also said that the remaining two-thirds of the financial literacy gap is explained by lower financial knowledge. Therefore, researchers concluded that <strong>enhancing the confidence of women</strong> when it comes to their financial knowledge in addition to the knowledge itself is essential to more effectively close the financial literacy gender gap.</p><h3>Now that is where Ellevest comes in!</h3><p>Ellevest adjusted the financial services industry to women and empowering them in their finances and lives.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/811/0*SmGrcuIw2ny9dZyd" /><figcaption>Ellevest’s instagram posts empower women and highlight personal finance concepts such as dollar cost averaging, financial self care, budgeting, building a healthy money mindset, and other #relatable posts. Learn more about Ellevest at<a href="https://www.ellevest.com/"> https://www.ellevest.com/</a>.</figcaption></figure><p>Meet <a href="https://www.ellevest.com/"><strong>Ellevest</strong></a>, a financial services company, fintech investment platform and industry disruptor <strong>“built by women, for women.” </strong>It<strong> </strong>brings investing, banking, financial planning, personalized digital investing, and career coaching together under unique membership plans. Its mission? Close the money gender gap by truly meeting the needs of women, and to get more women involved with investing their money and wealth. However, despite this, Ellevest welcomes men! They use gender-specific data to inform investing recommendations.</p><p>Founded by <a href="https://www.linkedin.com/in/salliekrawcheck/">Sallie Krawcheck</a> and <a href="https://www.linkedin.com/in/charliekroll/">Charlie Kroll</a> in 2014 under the scrutiny from many <a href="https://slate.com/human-interest/2015/10/financial-advice-just-for-women-seems-like-a-great-idea-its-not.html">skeptics</a>, Ellevest now manages over $1 billion with over 120,000 users, about 90% of whom identify as women (<a href="https://en.wikipedia.org/wiki/Ellevest">wikipedia</a>). Additionally, though the typical user is a woman in her 30s, Ellevest’s investors range from 18 to 106 years old.</p><p>Though I am not personally an Ellevest member, I have heard great things about them from friends who used Ellevest to get into investing and learn about how to use it to meet their financial goals right where they are in life! I have also followed Ellevest on <a href="https://www.instagram.com/ellevest/">Instagram</a> for a while now, and I applaud them for their branding and social media strategy that connects personal growth to money moves and <strong>empowers women </strong>to learn, save, and invest. From following Ellevest, I feel as though the company genuinely care about their users and daily needs and <a href="https://www.investopedia.com/terms/f/financial-health.asp#:~:text=Financial%20health%20is%20a%20term,fixed%20or%20non%2Ddiscretionary%20expenses.">financial health</a>. Here are some of the resources that Ellevest offers: <a href="https://www.ellevest.com/magazine">Ellevest Magazine</a> | <a href="https://www.ellevest.com/pricing-plans?ko_click_id=Cj0KCQjwiNSLBhCPARIsAKNS4_fxmd5GKV5jvwRpn2GPcxBTLCajbFhgMM9DqiFUWGl_bLkkcxqac6kaAjufEALw_wcB&amp;c1=GAW_SE_NW&amp;source=STL_USA_BRND&amp;cr2=search__-__nw__-__usa__-__brand&amp;kw=ellevest%20membership_e&amp;cr5=444108013602&amp;cr6=invest_like_a_women&amp;cr7=c&amp;utm_source=google&amp;utm_medium=cpc&amp;utm_campaign=usa-brand-membership&amp;utm_term=plans&amp;gclid=Cj0KCQjwiNSLBhCPARIsAKNS4_fxmd5GKV5jvwRpn2GPcxBTLCajbFhgMM9DqiFUWGl_bLkkcxqac6kaAjufEALw_wcB">Ellevest Memberships</a> | <a href="https://www.ellevest.com/atwork">Ellevest At Work</a> | <a href="https://www.ellevest.com/private-wealth-management/how-were-different">Ellevest Private Wealth Management</a>.</p><h3>Ellevest &amp; Threat of Substitutes.</h3><p>I decided to take a deeper dive on Ellevest through the lens of the impact they are having on the financial services industry and financial literacy through<a href="https://www.investopedia.com/terms/p/porter.asp"> <strong>Porter’s 5 Forces</strong></a>, which helps us understand a company’s environment, strengths, and weaknesses. I learned about this framework in depth through<a href="https://www.coursera.org/learn/uva-darden-foundations-business-strategy"> The Foundations of Business Strategy</a> course at the University of Virginia.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/960/0*G-4qYsKKkmeD3uKh" /><figcaption>Image from<a href="https://managementweekly.org/porters-5-forces/"> Management Weekly</a>.</figcaption></figure><p><strong>Threat of Substitutes, </strong>the last of Porter’s 5 Forces<strong>, </strong>refers to the threat posed by “substitute goods or services that can be used in place of a company’s products or services” (<a href="https://www.investopedia.com/terms/p/porter.asp">Investopedia</a>). As an investment advisor/roboadvisor, Ellevest enters a crowded arena with many potential substitutes. However, Ellevest identified a <strong>massive niche market</strong> that has been historically underserved in the financial services industry and NEEDS attention — <strong>Women</strong> (not just attention, the right attention!).<strong> </strong>Ellevest even made CNBC’s 2018 and 2019 List of 50 Disruptors because of this at number <a href="https://www.cnbc.com/2018/05/22/ellevest-2018-disruptor-50.html">24</a> and <a href="https://www.cnbc.com/2019/05/14/ellevest-2019-disruptor-50.html">45</a>, respectively.</p><p>Ellevest is currently the only robo-advisor out there for women still standing after <a href="https://worthfm.com/">WorthFM</a>, another company focused on women, launched around the same time but closed in 2018. WorthFM cited poor marketing efforts and its narrow focus on high network women as reasons why they failed. Ellevest on the other hand began with women of moderate wealth and effectively growing funding and investors before turning to high wealth women with the launch of Ellevest Private Wealth Management.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/0*lw6V9f05nOmMR5eB" /><figcaption>Image from <a href="https://twitter.com/Ellevest?ref_src=twsrc%5Egoogle%7Ctwcamp%5Eserp%7Ctwgr%5Eauthor">Ellevest’s twitter</a></figcaption></figure><p>Because of how well Ellevest has done killing the social media game, appearling to millenial women well, and focusing on real women’s needs when it comes to finances and learning, the threat of a substitute company that will do and can do what Ellevest does is low. However, of course with the rise of new and emerging technologies and cryptocurrencies, which are a<a href="https://www.ellevest.com/magazine/investing/cryptocurrency"> hard no in an Ellevest portfolio</a>, Ellevest will need to keep innovating and thinking about their stance in order to keep up with other companies and maintain their competitive advantage in a tech-driven world.</p><h3>More on Ellevest’s Core Competitve Advantage and Disruptive Factors.</h3><p>Ellevest’s <strong>core competitive advantage </strong>comes from them truly meeting real women’s needs in many spaces and synthesizing them well in one platform — financial literacy, investing, career growth — and doing so well in the way they design aspects of their products and services ranging from the UI to their investment strategy. They do it via <a href="http://production.assets.ellevest.com/documents/Ellevest-White-Paper.pdf"><strong>The Ellevest Difference and Methodology</strong></a> and focus on the following:</p><ul><li>Learning and resources to help with financial learning and literacy.</li><li>Carefully rethinking each step of goals-based investment from the bottom-up, considering their construction of their portfolios, selection of investments within them, and development of algorithms to drive forecasts and recommendations. For example, unlike many competitors, Ellevest uses up to 21 different asset classes across the goal-based portfolios.</li><li>Careful consideration of women’s different approaches to investing than men and the use of gender-specific data to inform investing recommendations. For example, women are often more goal-oriented when it comes to investment decisions, risk aware and prefer less volatility than men. Additionally, on average, women tend to live longer than men, take more time off from work to care for children, and have different salary arcs.</li><li>A modern, easy-to-use, and engaging user experience (UI/UX).</li><li>Creating a bold social media presence that appeals to real women investors and those getting into investing and financial literacy.</li></ul><p>Ellevest has a sauce, but it isn’t secret! If a company has the desire to, they could imitate them. However, since Ellevest does what they do and serve women so well compared to other companies that have tried and failed, it wouldn’t be wise for another player to imitate and do the same thing. Additionally, the common consensus may be that “women don’t need personal finance services just for them” and “don’t need all the pink washing and paternalistic sales pitches” (<a href="https://www.forbes.com/sites/nextavenue/2018/07/19/do-women-really-need-financial-advice-for-women/?sh=7ca77bd652d4">Forbes</a>). However, Ellevest’s main colors in their style guide does not include pink!</p><blockquote>“Son of a gun, the industry today has built a pink wall that I don’t think they meant to build, but that has kept women out.” ~ Ellevest CEO Sallie Krawcheck</blockquote><h3>Reflection &amp; What’s Next?</h3><p>Thank you for reading! In my <a href="https://k-lordi.medium.com/financial-literacy-the-role-of-the-news-media-industry-f98f73b78765">last post</a>, I wrote a meaningful high-level on financial literacy and the role of news, media, for-profits, and non-profit companies. In this one, I explored the financial literacy gender gap and dove deeper into the disruptive key player serving women’s needs, Ellevest, through the lens of their core competencies and Porter’s 5 Forces. I loved analyzing Ellevest, and I look forward to possibly writing about other audiences and communities to serve and target to improve financial literacy, inclusion, and accessibility in the United States and globally.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/890/0*L_YHDelmTziTszai" /><figcaption>For me, it’s buying fresh flowers for the kitchen and<a href="https://jackassburrito.com/"> Jackass Burrito</a> every other week.</figcaption></figure><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=4859f466d253" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Financial Literacy & the Role of the News & Media Industry.]]></title>
            <link>https://klordihavemercy.medium.com/financial-literacy-the-role-of-the-news-media-industry-f98f73b78765?source=rss-1f00722da339------2</link>
            <guid isPermaLink="false">https://medium.com/p/f98f73b78765</guid>
            <category><![CDATA[personal-finance]]></category>
            <category><![CDATA[medium]]></category>
            <category><![CDATA[financial-literacy]]></category>
            <category><![CDATA[cryptocurrency]]></category>
            <category><![CDATA[news]]></category>
            <dc:creator><![CDATA[Katherine Lordi]]></dc:creator>
            <pubDate>Mon, 04 Oct 2021 03:15:03 GMT</pubDate>
            <atom:updated>2021-10-10T21:48:40.667Z</atom:updated>
            <content:encoded><![CDATA[<h4>A quick deep dive in America.</h4><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*gdd5jvPDgDaGYUgrkt1n9g@2x.jpeg" /><figcaption>“Yes these are real credit cards that real people left here.” (Credit <a href="http://www.drinkersrittenhouse.com/">Drinker’s pub</a> in Philadelphia)</figcaption></figure><h3>Here are a few awakening statistics… 👀</h3><ul><li>Nearly <strong>3/4 </strong>workers said they are in debt, and <strong>more than half </strong>think they always will be according to a <a href="https://www.forbes.com/sites/zackfriedman/2019/01/11/live-paycheck-to-paycheck-government-shutdown/?sh=66000fcb4f10">2017 CareerBuilder Survey</a>. This makes sense as to why <strong>63%</strong> of young Americans ages 18–34 have high levels of financial stress, which very likely increased during the COVID pandemic (<a href="https://www.usfinancialcapability.org/downloads/NFCS_2018_Report_Natl_Findings.pdf">2018 FINRA study</a>).</li><li><strong>3/5 </strong>adults do not have a budget according to a <a href="https://www.nfcc.org/resources/client-impact-and-research/2019-consumer-financial-literacy-survey/">2019 survey</a>. Monthly budgets are fundamental for monitoring spending and paying off debt.</li><li>In 2021, the total <strong>student loan debt reached a high of </strong><a href="https://www.cnbc.com/2021/09/09/america-has-1point73-trillion-in-student-debtborrowers-from-these-states-owe-the-most.html#:~:text=In%20the%20United%20States%2C%20student,%241.73%20trillion%20in%20student%20loans."><strong>$1.73 trillion</strong></a>, a <strong>91% increase</strong> in the past decade. Additionally, credit card debt in the U.S. is at a <strong>record high of $1 trillion</strong>, meaning that many Americans deal with high interest rates and late fees that can lead to vicious cycles of debt. These are some symptoms of the <a href="https://www.pewresearch.org/social-trends/2020/01/09/trends-in-income-and-wealth-inequality/"><strong>growing, doubling wealth gap</strong></a> between the richest and poorest families during the past 30 years.</li></ul><h3>The bottom line is that America &amp; the world struggles with financial literacy, &amp; I want to help!</h3><p>In my career,<strong> I am an Associate Product Manager in News, Data &amp; Media </strong>focused on enhancing our audiences’ digital experiences with our trusted content, as well as empowering them to make important decisions in their lives. <strong>I am also a volunteer at the nonprofit </strong><a href="https://finmango.org/"><strong>FinMango</strong></a><strong> </strong>dedicated to rethinking impact for financial literacy and inclusion for youth and around the globe. I’m so thankful to be so excited and passionate about what I do!</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/170/1*mVlQ69vLnsu7YAiIf4RyaA.png" /><figcaption>Check out FinMango and what we do <a href="https://finmango.org/">here</a>!</figcaption></figure><p>Due to the <strong><em>intersection of finance-related content and news, journalism, &amp; media</em></strong> (hence the need for readers to be more financially literate to better understand and apply such content to their lives), I’m diving deeper to help make a positive impact as a developing leader and product manager in these intersecting spaces. I’m especially interested in investment education for youth and helping marginalized communities.</p><h3>Key players: Business-focused news &amp; media in the United States.</h3><p>In addition to being publications that enable readers to watch the markets and read global news, business news, etc., these key players incorporate content that helps support efforts around financial literacy. For instance, <a href="https://www.cnbc.com/money101/">CNBC has a newsletter in partnership with Acorns called Money 101</a>, <a href="https://www.wsj.com/articles/how-to-teach-wsj-investing-challenge-11629810602">WSJ has a 5-Week Investing Challenge</a>, Barron’s has an <a href="https://www.barrons.com/newsletters">intro How to Invest email series</a>, and the <a href="https://www.morningbrew.com/money-scoop">Morning Brew has the Money Scoop newsletter</a>, just to name a few.</p><p>Additionally, many companies such as the <a href="https://www.nytimes.com/column/your-money">NY Times</a>, <a href="https://www.wsj.com/questions/money?mod=nav_top_subsection">WSJ</a>, and <a href="https://www.businessinsider.com/personal-finance">Business Insider</a> are working on providing and better surfacing <a href="https://en.wikipedia.org/wiki/Evergreen_(journalism)">evergreen content</a> and “how-to” guides about managing personal finance while providing attractive student subscription offerings.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/0*jwRZ9ABwWfeRLF8X.png" /><figcaption><a href="https://www.wsj.com/questions/money?mod=nav_top_subsection">WSJ Money Section</a></figcaption></figure><p>However, despite making strides to engage and attract new audiences by focusing on financial literacy and other topics of interest, many of these companies face challenges and <strong>barriers to subscriber growth</strong> for young audiences (ages 18–40), individuals from lower income communities, and women due to factors such as cost to subscribe, political skewness, <a href="https://en.wikipedia.org/wiki/Media_literacy">news literacy</a>, or not believing the publication is “for them” due to brand perception. The future of each company may depend on how each addresses these challenges. With these barriers in mind, can the news and media ever play a role in helping to close the wealth gap (big question I wonder)?</p><h3>How other for-profit and non-profit companies aim to improve financial education.</h3><p>Most financial services company websites have some sort of learning or education tab! For example, <a href="https://www.schwabmoneywise.com/moneywise-america">Charles Schwab</a>, <a href="https://learn.robinhood.com/">Robinhood</a>, <a href="https://www.coinbase.com/learn">Coinbase</a> (for Cryptocurrency), and many more strive to improve financial literacy among potential and current customers while using financial education as a marketing tool. Many of these players put their own unique spin on it to make financial education “more cool 😎.” For example, <a href="https://step.com/money-101">Step (mobile banking for teens)</a> markets heavily on social media and took advantage of TikTok’s growth among Gen Zers, being promoted by influencers such as <a href="https://techcrunch.com/2020/12/02/teen-banking-service-step-raises-50m-adds-tiktok-star-charli-damelio-to-investor-list/&#39;">Charli D’Amelio</a>. <a href="https://www.chime.com/21savage/">Chime and rapper 21 Savage</a> are also teaming up to spread financial literacy.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/0*UOw5ro4FmknjytSe.jpg" /><figcaption>Charli D’Amelio, TikTok’s most-followed content creator, <a href="https://www.dexerto.com/entertainment/charli-damelio-invests-in-50-million-banking-service-for-teens-1473498/">invested in Step</a> as her first startup investment. This Visa card allows teens ages 13–19 establish credit early and combat student loans.</figcaption></figure><p>Even though the financial services industry largely funds the financial education industry, nonprofit organizations such as <a href="https://finmango.org/">FinMango</a>, <a href="https://www.ngpf.org/">Next Gen Personal Finance</a>, and <a href="https://www.jumpstart.org/">Jump$tart</a> have a mission to advance financial education for youth and make it accessible and useful. Additionally, for-profit companies such as <a href="https://www.askfinny.com/">Finny</a> and <a href="https://www.ramseysolutions.com/?utm_source=google&amp;utm_id=go_cmp-197939186_adg-10546208306_ad-482007255966_kwd-42626442_dev-c_ext-_prd-&amp;gclid=CjwKCAjwqeWKBhBFEiwABo_XBnjHVEi3_OgGNecqO0Ndjz9pw8GUur1pgEKUeedaelZ7ZHqkMItJfxoCP4MQAvD_BwE">David Ramsey Solutions</a> help individuals learn, apply their knowledge, join a community, and/or get out of debt.</p><h3>What’s Next?</h3><p>I just touched on a lot here but hope my writing provided a meaningful high-level on Financial Literacy &amp; the Role that the News &amp; Media Industry as well as other types of companies play in it.</p><p>Next, I will explore a specific company working to enhance financial literacy and inclusion efforts with high impact. Stay tuned, and thank you for reading! :)</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=f98f73b78765" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Exercise: Analyze & Elevate Your Tribe To Better Align With Your Values]]></title>
            <link>https://klordihavemercy.medium.com/exercise-to-do-often-in-life-analyze-elevate-your-tribe-480ed885ff25?source=rss-1f00722da339------2</link>
            <guid isPermaLink="false">https://medium.com/p/480ed885ff25</guid>
            <category><![CDATA[teamwork]]></category>
            <category><![CDATA[worry]]></category>
            <category><![CDATA[career-development]]></category>
            <category><![CDATA[connection]]></category>
            <category><![CDATA[self-improvement]]></category>
            <dc:creator><![CDATA[Katherine Lordi]]></dc:creator>
            <pubDate>Fri, 02 Jul 2021 15:22:19 GMT</pubDate>
            <atom:updated>2021-08-10T18:43:55.595Z</atom:updated>
            <content:encoded><![CDATA[<h4>Something To Do Often in Life!</h4><p>In this Medium, I write a personal reflection and go through an exercise (shoutout to the <a href="https://www.morningbrew.com/daily">Morning Brew’s</a> <a href="https://foundersjournal.morningbrew.com/">Founder’s Journal Podcast</a>) to analyze and elevate your tribe to better align to your personal values and goals. <strong>Our tribes consist of our personal connections, role models, communities, and content. It is important to methodically build our tribes because we are the products of all of these inputs in our lives. </strong>On my end, I think that it is a good time to do this exercise since I’m going through a career transition and have been feeling very ambitious lately. Try it on your own! Additionally living in this digital age where the internet has made connection with people and things so easy, we have so many more connections that we need to ensure are valuable to us and our well-beings.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*HlYFm0yX-qWiOH1XY15Vjw.jpeg" /><figcaption>How many times have we all heard this? Image by <a href="https://quotefancy.com/quote/11593/Jim-Rohn-You-are-the-average-of-the-five-people-you-spend-the-most-time-with">QuoteFancy</a>.</figcaption></figure><h3>Personal Reflection</h3><h4>One of my Why’s for Intentionally Working On My Tribe.</h4><p><strong>What you worry about it what you worship, </strong>and<strong> </strong>a<strong> </strong>few months ago, I found myself falling into this trap while struggling with worry more than usual. These worries stemmed from me navigating the beginning of my career, striving for success in my twenties and how to get it, navigating friendships and relationships, and living in a pandemic year, which has impacted us all internally and externally. All of us can relate, and I’m thankful that I am self aware of my worry and how it got worse during this time so that I can take back control, live happier, and always be thankful for everything in my life :).</p><p>Remember that we all worry, and that it’s okay because our worries and anxieties do not define us. <strong>Rather, what defines us more is how we learn from our failures and environments, move forward in the face of adversity and challenges, and strive to improve everyday to be better to ourselves and others. </strong>For myself, I’ve found that immersing myself in community and surrounding myself with people who challenge me and inspire me has energized me to be a better me and take action rather than worry about things I cannot control.</p><h4>Thank You Self Development Podcasts!</h4><p>I enjoy listening to podcasts focused on building ourselves and careers and recently started listening to the <a href="https://foundersjournal.morningbrew.com/"><strong>Founder’s Journal</strong></a><strong> Podcast by Alex Lieberman</strong>, Co-Founder and CEO of the Morning Brew. The episodes <a href="https://open.spotify.com/episode/0aaDRW4xA7muDIPEvE0x9Z?si=76202a3fa44c42ad">How to Build Your Tribe</a> and <a href="https://open.spotify.com/episode/6hJ2JSkicaLeXd9VaPx3p1?si=5cf390c4ac274515">How to Elevate Your Tribe</a> resonated with me a lot because I look forward to being apart of more meaningful communities and continuing to develop meaningful connections and relationships in my life, especially after the pandemic year. I highly recommend giving these podcasts and the Founder’s Journal a listen. I especially love to in the morning when beginning my work day.</p><blockquote>Your tribe is a combination of all things that you spend the most time connecting with — Personal 1:1 Connections, Communities, Role Models, and Content ~ Alex Lieberman, Co-Founder and CEO of the <a href="https://www.morningbrew.com/daily">Morning Brew</a></blockquote><p>In the rest of this Medium, I go through an exercise on paper to analyze my current tribe, look at how my current tribe aligns with my values and goals, and identify actions I can take to elevate my tribe going forward. I’m writing this introduction and reflection before I even fully went through the exercise, but I’m looking forward to learning form the experience and improving my everyday from it. As Alex puts it in the podcast, <strong>building our tribes intentionally and auditing it regularly “is the bedrock of being a fulfilled and successful leader,” helps us accomplish our goals, and helps us become the person we want to become.</strong></p><h3>THE EXERCISE: 2 Sheets of Paper.</h3><p>My handwriting is not the neatest I apologize! However, please read on to see the value I got from this exercise.</p><h3>Sheet #1: Your Current Tribe</h3><p>On a piece of paper, I spent 10 minutes outlining my current tribe consisting of my 1-on-1 personal connections, virtual/physical communities, content I take in, and role models. I think I hit the major ones, but I would probably iterate on this if I were to do it again. Additionally, I divided these categories up by time (daily, weekly, monthly, and bi-yearly) since in our lives, we don’t interact with all of our tribe tribe equally and doing this helped me visualize potential areas of growth.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*Tjho3vGi1Y694DpMTOMC4g.jpeg" /><figcaption>My Sheet #1: My Current Tribe (Draft). Blocking out my friends’ names for privacy!</figcaption></figure><h3>Sheet #2: Your Personal Values</h3><p>On the second sheet of paper, I spent 10 minutes writing my values and connected them to my name circle. Our values are important to keep at the forefront of everything we do because of how important they are to us, how we desire to live our lives, and the impact we want to have → purpose, happiness, and fulfillment.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*zfU6N3fEENfOsks46tnw9w.jpeg" /><figcaption>Sheet #2: My Top 8 Values — Challenge, Growth, Contribution, Health, Integrity, Fun, Curiosity, Family</figcaption></figure><p>Here are key words and phrases I think of when each value comes to mind:</p><p><strong>Challenge: </strong>Practice makes perfect; Build off the fundamentals; Apply my knowledge and learning in new ways; Make connections between things that may not be the most apparent; Think creatively &amp; differently; Improve a little bit each day to reach my goals and then set new ones.</p><p><strong>Growth: </strong>Embracing the learning journey and the process; Understanding that it is not always linear; Failing forward.</p><p><strong>Contribution:</strong> To society; To give back and help others in need; To use my talents for others; To my family and people I care about.</p><p><strong>Health: </strong>Physical, Mental, Emotional, Social, Environmental for myself and supporting those around me.</p><p><strong>Integrity:</strong> Striving to do the right thing reliably and responsibly; Staying true to my values and the things I believe in and standing up for those things; Encompasses a lot.</p><p><strong>Fun:</strong> In the little things; In learning about new things; In new adventures and experiences; In media; In nature; In friends; In family; In games + competition; In every aspect of life even work.</p><p><strong>Curiosity:</strong> How can we do this better?<strong> </strong>Desiring to learn from others and taking advantage of those conversations to learn; Actively seeking to learn about new topics outside our areas of expertise; Taking advantage of new opportunities thrown our way.</p><p><strong>Family: </strong>First! Always being there for those who have always been there for me, loved me, supported me; Having fellowship with a feeling of fellowship /with others as a result of sharing common attitudes, interests, and goals; Building communities.</p><h3>Modifying Sheet #2: Connecting Your Current Tribe With Your Values.</h3><p>Now, this is where this becomes fun, visual, and eye-opening. Analyzing our Tribe = Sheet #1 + Sheet #2. In this part of the exercise, assign members of your tribe on Sheet #1 to your values by writing them and connecting them to values on Sheet #2. This part of the exercise took about 20 minutes. Even though doing this made my paper a little bit messy and even less legible, that’s okay! The goal is to visualize which members of your tribe connect to your values and which do not! For example, for me, it didn’t feel natural to connect Social Media to any of my values, so I didn’t write it down. Therefore, I think this is valid reason to delete my Social Media apps from my phone sometimes so that I don’t use them on a daily basis. Making note of things like this is part of the point of this exercise.</p><p>Looking back on Sheet #1, I forgot a few members of my tribe and added some additions. In faint yellow sharpie, you can also see the newer elements of my tribe that have especially positively impacted my life this year in 2021.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*8Ryp2-8Gi3-3MDxzRaNf0g.jpeg" /><figcaption>Analyzing the Tribe = Sheet #1 + Sheet #2 or Analyzing the Tribe = Values + Current Tribe.</figcaption></figure><h3>Modifying Sheet #2 Again: Highlighting Unoccupied Areas as Opportunity to Elevate My Tribe</h3><p>Analyzing the Tribe = Sheet #1 + Sheet #2 + Highlighting Areas that are Unoccupied. For the final part of this exercise, I took 5 minutes, used a red marker, and drew some blobs on the page to highlight areas of opportunity to elevate my tribe. Looking at my paper, I see a variety of areas of opportunity for me to elevate my tribe for specific personal values. Nice.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*PTsNIIEV4xAwCnY2h5nSyQ.jpeg" /><figcaption>Analyzing the Tribe = Sheet #1 + Sheet #2 + Unoccupied Areas or Analyzing the Tribe = Values + Current Tribe + Areas of Opportunity to Elevate Your Tribe.</figcaption></figure><p>Looking at my paper after highlighting unoccupied areas within each value, I see areas of opportunity and growth for my tribe! For example, I found that there is room for me to be a bit more challenged by my tribe. Therefore, I’ll identify some actions I can take, content I can add, and connections I can make in order to create a tribe that challenges me more to help me grow, improve, and learn.</p><h3>Final Step: Identify Actions to Take &amp; JUST DO IT.</h3><p>Reflecting on this exercise, I identified a few actions (I’m just brainstorming for now as this is a draft and I will make them more specific and actionable later) that I want to take to elevate my tribe consisting of my personal connections, communities I’m apart of, content I take in my mind, and role models for the remainder of this year!</p><ul><li>Find a new mentor or connect with an existing mentor who will challenge me on a monthly or bi-yearly basis.</li><li>Find 2 more role models and spend time to understand their life path, voice, values, and how they align with mine so that I can truly say and explain why they are role models to me.</li><li>Focus on my mental health a little bit more. Find something to do daily, weekly, or monthly to rejuvenate myself a bit in this area. When I wrote this, I still needed to hash out these next steps, but I just did The <a href="https://www.linkedin.com/learning/the-six-morning-habits-of-high-performers/make-truthful-affirmations?u=2104649">Six Morning Habits of High Performers</a> on LinkedIn Learning and will be adding 10 minutes of intentional meditation to my daily routine! Why? When you sit in silence, it is scientifically proven that you will lower your stress, improve your clarity, and helps you gain new insights. Practice makes perfect, and I will intentionally do this and add it to my planner from now on. Rant over.</li></ul><h3>Finally, Reflecting on this Exercise &amp; Reflection :).</h3><p>Looking back on this exercise and on my accomplishments this past year, I’m very proud of myself and how far I have come! As Alex Lieberman put it at the end of the podcast, <strong>“One of the fastest ways to become your values (and reach your goals) is to surround yourself with a tribe that lives those values.” </strong>I have a good tribe, and I’m going to make it even better.</p><p>Thank you for reading! Once again, I highly recommend listening to the <a href="https://foundersjournal.morningbrew.com/"><strong>Founder’s Journal</strong></a><strong> Podcast </strong>by Alex Lieberman and the episodes <a href="https://open.spotify.com/episode/0aaDRW4xA7muDIPEvE0x9Z?si=76202a3fa44c42ad"><strong>How to Build Your Tribe</strong></a><strong> and </strong><a href="https://open.spotify.com/episode/6hJ2JSkicaLeXd9VaPx3p1?si=5cf390c4ac274515"><strong>How to Elevate Your Tribe</strong></a><strong> </strong>and trying this exercise yourself! I’ll return to it and this Medium post in the future. Let me know if you have any thoughts or other podcasts or articles to read about related to this (or not).</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=480ed885ff25" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Healthy Reminders for the Soft-Spoken, Visionary INFJ ☁️]]></title>
            <link>https://klordihavemercy.medium.com/healthy-reminders-for-the-soft-spoken-visionary-infj-%EF%B8%8F-ad8eac52e0b8?source=rss-1f00722da339------2</link>
            <guid isPermaLink="false">https://medium.com/p/ad8eac52e0b8</guid>
            <category><![CDATA[personality-types]]></category>
            <category><![CDATA[mbti]]></category>
            <category><![CDATA[personality]]></category>
            <category><![CDATA[self-improvement]]></category>
            <category><![CDATA[infj]]></category>
            <dc:creator><![CDATA[Katherine Lordi]]></dc:creator>
            <pubDate>Mon, 01 Mar 2021 05:39:13 GMT</pubDate>
            <atom:updated>2021-03-06T23:39:37.509Z</atom:updated>
            <content:encoded><![CDATA[<figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*mEOsoaQZnORsOWw69WLHLQ.png" /><figcaption><strong>I️NFJ = Introverted, Intuition, Feeling, &amp; Judging</strong></figcaption></figure><p>In this article, I break down my <a href="https://eu.themyersbriggs.com/en/tools/MBTI">Myers-Briggs</a> personality type <a href="https://eu.themyersbriggs.com/tools/mbti/mbti-personality-types/infj"><strong>I, N, F, J</strong></a><strong> </strong>and discuss some <strong>healthy reminders that I find help me be a better me</strong>, touching upon things such as nutrition, productivity, giving back, self care, and relationships.</p><p>Writing this as a reflection has helped me better understand myself and embrace me and my personality, but the reminders are something that others of different personality types can relate to and take away from as well!</p><p>Apparently INFJ is the <a href="https://introvertdear.com/news/infj-secrets/">rarest personality type</a>, making up about 2.3% of the world’s population. Backed by psychology, the <a href="https://eu.themyersbriggs.com/en/tools/MBTI/MBTI-personality-Types">Myers-Briggs Questionaire</a> indicates your personality type in 4 dimensions: Where you focus your attention — Extraversion (E) or Introversion (I); The way you take in information — Sensing (S) or INtuition (N); How you make decisions — Thinking (T) or Feeling (F); &amp; How you deal with the world — Judging (J) or Perceiving (P).</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/463/0*f8tpU0TAXaq6y4Xq.png" /><figcaption><a href="http://danigirl.ca/tarot/2020/04/22/tarot-and-myers-briggs-personality-indicators/">The 16 Myers-Briggs Personality Types</a> Which one are you?</figcaption></figure><h3>What Are INFJ’s Like?</h3><h4>INFJs in a Nutshell</h4><ul><li>Value living with purpose and mission for their lives.</li><li>“Live to solve problems and bring about positive change” (<a href="https://www.truity.com/personality-type/INFJ">Truity</a>).</li><li>“Take concrete steps to realize their goals and make a lasting impact.”</li><li>“Are compassionate and quietly inspiring; they enjoy helping others grow” (<a href="https://eu.themyersbriggs.com/tools/mbti/mbti-personality-types/infj">Myers-Briggs</a>).</li></ul><p>They lean more towards these personality dimensions:</p><p><strong>Introverted: </strong>Energized by quiet time alone; Focus more internally</p><p><strong>Intuition: </strong>Pay more attention to ideas, concepts, and interpretations over facts and details</p><p><strong>Feeling: </strong>Prioritize relationships and others’ needs; Make decisions more based on gut feelings</p><p><strong>Judging: </strong>Prefer organization and plans (<a href="https://www.truity.com/personality-type/INFJ">Truity</a>)</p><h4>Strengths</h4><p>Mission-Oriented; Peace Makers; Inspiring others; Work with Integrity; Value deep &amp; authentic relationships; Love to learn and solve challenges to help others</p><p>Altruistic, Visionary, Charismatic, Curious, Creative, Passionate, Grounded; Cooperative, Compassionate, Caring, Loyal, Organized, Dependable, Determined, Intelligent, Insightful, Independent</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/992/0*RwKh709RUDdIx7FG" /><figcaption>Sorry for bombarding you with adjectives. See <a href="https://share.themyersbriggs.com/en-US/Type-Heads">here</a> for type heads of other personality types.</figcaption></figure><h4><strong>Can Be Both a Strength &amp; Weakness</strong></h4><p>Intense; Quiet at first; Future-focus; Wish they could know everything; Have a complex mind; Need time to think privately; Wear hearts on their sleeve; Prefer order</p><h4><strong>Areas of Development</strong></h4><p>Perfectionistic; Procrastinate at times;<strong> </strong>Sensitive to Criticism; Overthinkers; Conflict-averse; Likely stressed when feeling under-appreciated; Prone to burnout; Critical of self and others; Get too caught up in the big picture and may overlook details; Learn to be okay with small talk lol</p><h3>Reflecting On Some Healthy Reminders for INFJs</h3><p>Reflecting on important areas of life through the lens of my personality type and recording reminders has been a meaningful experience! I try to take these to heart everyday to be on my A game.</p><h4>1. On Nutrition &amp; Body Image: Eat intuitively, enjoy every bite, &amp; don’t take it for granted.</h4><p>Actively practicing<strong> </strong><a href="https://www.intuitiveeating.org/10-principles-of-intuitive-eating/"><strong>Intuitive Eating</strong></a>, an evidenced-based, non-diet, &amp; self-care eating framework, has improved my life alot— improving my energy levels throughout the day, confidence, fitness, &amp; my <strong>relationship with food and calories and my body.</strong></p><p>As an INFJ, one of my core strengths is my <strong>consistency</strong> but a couple weaknesses are <strong>perfectionism and intensity</strong>. Knowing that our health is the most important thing, the diet mentality and dealing with an eating disorder for years mitigated strengths I’m proud of as an INFJ as I sought unattainable perfection through unhealthy habits and extremes. I am so much happier and healthier eating intuitively and focusing on proper nutrition for my body.</p><p>Additionally, I along with so many others are so fortunate to have easy and daily access to healthy foods and clean water. I don’t ever want to take it for granted. In the Philadelphia area, 1 in 5 people face hunger. Something that I will better implement in my life as I save and invest wisely for my future is to truly champion healthy grocery shopping on a budget and to donate some of the money I save to help people in need monthly. Some organizations whose mission is to end the hunger crisis in the Philadelphia area include <a href="https://www.philabundance.org/">Philabundance</a>, <a href="https://mannaonmain.org/">Manna on Main Street</a>, and <a href="https://www.riseagainsthunger.org/">Rise Against Hunger</a>.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/756/1*FEL1vcKlTmaFgILNtBZPag.jpeg" /><figcaption><a href="https://nutritionstripped.com/what-is-intuitive-eating/">10 Principles of Intuitive Eating</a></figcaption></figure><h4>2. On Productivity: Have a strategy to stop procrastination in its tracks.</h4><p>INFJs are <strong>visionary</strong> individuals who strive to make a lasting impact and solve big challenges. However, being perfectionistic<strong> </strong>and knowing that doing good work takes time, INFJs may procrastinate since huge endeavors are daunting. Yup, I fall into this trap at times. Here are some tips that help me stop procrastinating.</p><ol><li>Slow down and do one thing at a time and beware of multi-tasking. Read more here about the <a href="https://www.mheducation.com/highered/insights-ideas/multitasking-helpful-or-harmful.html">dangers of multi-tasking</a>.</li><li>Check your phone less and stay off social media during work. I try to only pick up my phone to answer messages or change the song or podcast.</li><li>Set aside time blocks to work on different projects and tasks. Here are some <a href="https://www.entrepreneur.com/article/332290">timeblocking tips</a>.</li><li>Truly enjoy the journey and learning process to reach your goals, and break them down into manageable objectives and tasks. Also, record your goals and tasks using whatever means works for you to hold yourself accountable. See more on this below.</li></ol><h4>3. On Success: Enjoy learning &amp; the journey to reach your goals. Don’t be overwhelmed you’re doing awesome.</h4><p>As individuals working towards self-improvement, we strive to capitalize on our strengths and diminish our weaknesses. Being an INFJ, some of my areas of development include overthinking, perfectionism, being critical of myself, and being prone to burnout as a result, which definitely impacts my overall happiness and productivity.</p><p>On the other hand, I embrace my strengths of my personality such as being <strong>organized</strong>, <strong>mission-oriented</strong>, having a<strong> love of learning, </strong>and <strong>seeing problems through. </strong>By focusing on my strengths and that my true happiness stems from teamwork and having a fulfilling vision<strong> </strong>for myself (that I am still figuring out of course), I’m confident in my ability to better handle stress, be kinder to myself, and <strong>embrace the journey as I work towards my goals.</strong></p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*zLvFOEJIqAQ7PYIAz0OdEw.png" /></figure><p>To do this, <strong>I simplify my life</strong>. I break down my <a href="https://www.atlassian.com/blog/productivity/how-to-write-smart-goals"><strong>S.M.A.R.T. goals</strong></a><strong> </strong>that align with my purpose into <strong>manageable objectives</strong> and <strong>specific tasks</strong> to complete each day. I write these down to hold myself accountable each day and feel accomplished checking them off. Knowing that reaching milestones, no matter how small, are wins towards my goals, I am able to have more fun and enjoy the journey to get to where I want to be.</p><h4>4. On Relationships: You know your heart, so don’t worry be happy :).</h4><p>In friendships and romantic relationships, INFJs are bold and<strong> value genuine and deep connections above all.</strong> INFJs care about a balance between fun and seriousness in a relationship and seek compatibility, attraction, sincerity, good communication, and depth, which takes time to find and develop. They truly value <a href="https://www.gottman.com/blog/importance-of-integrity/#:~:text=Simply%20put%2C%20integrity%20is%20doing,kind%2C%20understanding%2C%20and%20loving.">integrity in the relationship</a> and strengthening a connection while balancing individual growth. “Relationships with Advocates are not for the uncommitted or the shallow” (<a href="https://www.16personalities.com/infj-relationships-dating">16 Personalities</a>). INFJs also strongly desire to maintain harmony and are highly motivated to resolve conflicts (<a href="https://www.truity.com/personality-type/INFJ/relationships">Truity</a>).</p><p>Yup I will not be opening up much about this haha, but this definitely describes me and the aspects that I care about most in a relationship. My key reminder for myself and others who value similar things is to not worry because you know your heart, give all this to others, and deserve nothing less.</p><p>One area of development for INFJs is that they may feel especially stressed in times of conflict or uncertainty, causing them to overthink and get in their heads. In the past, I felt that these feelings were amplified while in a relationship or one that was ending because I cared so much. Worry less and try not to overthink because you have so much worth and are passionate about so much.</p><h4>5. On Passions: Keep doing what lights you up &amp; using your talents to help others.</h4><blockquote>“Nothing lights up Advocates like creating a solution that changes people’s lives.” (<a href="https://www.16personalities.com/infj-personality">16 Personalities</a>).</blockquote><p><strong>Solving problems to help others, volunteering, &amp; pursuing passions are key outlets for INFJs</strong> and are essential to their purpose. If you resonate, never lose this love because it lights you up. In the career side of my life for example, I’m passionate about tech innovation, designing and developing tools that help people, and telling meaningful stories through data.</p><p>Since INFJs more introverted and prefer to think privately first, they come across as quiet and soft-spoken. However, INFJs are passionate and bold about their passions, ideas, helping others, and problem solving to make a lasting impact. They rarely settle for “good enough,” and are willing to work extremely hard on complex challenges and see problems through until the end. Because of this, INFJs need to remember to take care of themselves too sometimes.</p><h4>6. On Self Care: Remember to prioritize taking care of yourself properly.</h4><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*wabC6VADt3o06Mlo7m1ZGw.jpeg" /><figcaption>Gainz</figcaption></figure><p>As I just mentioned, in order to prevent burnout and be their best, INFJs need to <strong>remember take proper care of themselves</strong>. In my life, I know that I need to prioritize nutrition, working out, and getting enough sleep every single day in to be happy and perform my best.</p><p>Additionally, it’s important to put effort and time into our health and wellbeing and give yourself bandwidth to. In my life, doing research, having discussions with others, and learning more in-depth about nutrition, fitness, and healthy sleep techniques went a long way to enable me to actually take proper care of my mind and body. However, it’s okay to not be the best or perfect with all this. Don’t be too hard on yourself.</p><h3>Final Thoughts: Be More Kind To Yourself</h3><p>To wrap up, here are some additional kind reminders for each of the areas I touched on. As an INFJ, I need to be less critical of myself and worry less, and I think these extra ones help with that.</p><ol><li><strong>On Nutrition &amp; Body Image: </strong>Appreciate what you have, and you don’t have to be perfect!</li><li><strong>On Productivity: </strong>Try to not procrastinate but don’t worry if it happens once in a while.</li><li><strong>On Success:</strong> It is not linear. <a href="https://www.joyenergytime.com/fail-forward/">Fail forward, fail fast, &amp; fail often</a>.</li><li><strong>On Relationships: </strong>Same thing. You know your heart, so don’t worry be happy :).</li><li><strong>On Passions: </strong>Just keep going it lights you up. Schedule time to volunteer and give back to others.</li><li><strong>On Self Care (I just touched upon it, there is so much more!): </strong>Remember to also just be, enjoy the ordinary things in life, and be thankful everyday for every blessing and friends and family. INFJs can struggle with that sometimes since they are very forward-thinking. Balance both self care and hard work for better performance (<a href="https://www.mayoclinic.org/healthy-lifestyle/adult-health/in-depth/work-life-balance/art-20048134">Work/Life Balance</a>). Also be in community with others! Don’t live life alone and embrace community more wherever you can find it even in challenging COVID times.</li></ol><p>I am thankful to have had the opportunity to take the full <a href="https://eu.themyersbriggs.com/en/tools/MBTI/MBTI-personality-Types">Myers-Briggs Questionaire</a> in college, and it was fun to reflect on my characteristics as an INFJ again in 2021 to lay out healthy reminders for life. I hope that they are something that others of different personality types may relate to and take away from as well.</p><p>Thank you for reading! Feel free to reach out to me to talk or discuss anytime, and I appreciate feedback as I try to write about more projects and topics I’m passionate about.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*nSiQNpD_d-ZaKL8kBL7r8w.png" /><figcaption>Other half of the ☁️☁️☁️ pic. Taken at Peace Valley Park, PA in Summer 2020</figcaption></figure><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=ad8eac52e0b8" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Data Science Project Reflection: What I Learned From the 2021 NFL Big Data Bowl ]]></title>
            <link>https://klordihavemercy.medium.com/data-science-project-reflection-what-i-learned-from-the-2021-nfl-big-data-bowl-1d515b2e54c1?source=rss-1f00722da339------2</link>
            <guid isPermaLink="false">https://medium.com/p/1d515b2e54c1</guid>
            <category><![CDATA[data-science]]></category>
            <category><![CDATA[sports-analytics]]></category>
            <category><![CDATA[nfl]]></category>
            <category><![CDATA[ai]]></category>
            <category><![CDATA[machine-learning]]></category>
            <dc:creator><![CDATA[Katherine Lordi]]></dc:creator>
            <pubDate>Thu, 18 Feb 2021 12:12:55 GMT</pubDate>
            <atom:updated>2021-02-18T12:51:27.709Z</atom:updated>
            <content:encoded><![CDATA[<p>Hello :)! I hope this is an informative and fun reflection to read if you are at all interested in <strong>Sports Analytics, Data Science, Machine Learning (ML), Python Programming, &amp; AI in Sports.</strong> Though a bit long, I keep it organized and link a lot of sources if you are interested in learning more.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/995/1*MSOG4BGhklUWBlqSi7_CCQ.png" /><figcaption><a href="https://operations.nfl.com/gameday/analytics/big-data-bowl/">NFL Operations presents the Big Data Bowl 2021</a></figcaption></figure><h3>Intro. &amp; I Was Pumped for Super Bowl Sunday</h3><p>Writing this reflection in the spirit of Super Bowl LV (Big <a href="https://www.chiefs.com/team/coaches-roster/andy-reid">Andy Reid</a> Fan), I took time to reflect on what I learned doing the <a href="https://operations.nfl.com/gameday/analytics/big-data-bowl/"><strong>NFL Big Data Bowl 2021 Analytics Competition</strong></a>.<strong> </strong>My submission is named <a href="https://www.kaggle.com/ktl008/defensive-back-domination-nfl-big-data-bowl-2021">Defensive Back Domination</a> and has a summary of my outcomes at the top. Though I did not win (I did not expect to), I had fun, practiced data science, and learned alot from and was so impressed by the <a href="https://www.kaggle.com/c/nfl-big-data-bowl-2021/discussion/217170">winning submissions</a>.</p><p><em>This year’s challenge was to use data to help evaluate defensive performance on pass plays,</em> which was definitely challenging to tackle yet important since metrics for measuring NFL defenses lag behind offenses. Check out <a href="https://www.kaggle.com/c/nfl-big-data-bowl-2021/overview">kaggle</a> for full competition details and <a href="https://nextgenstats.nfl.com/">NextGenStats</a>, which provides the position and speed of every player on the field during each play. My two goals for this reflection are:</p><ol><li><strong>Document my technical process and aspects to learn from and improve.</strong></li></ol><ul><li><strong>Data Preparation &amp; Exploratory Data Analysis</strong></li><li><strong>Feature Engineering &amp; Visualizations using Matplotlib</strong></li><li><strong>ML Model: XGBoost Decision Trees to Classify Pass Result</strong></li><li><strong>Presenting the Results</strong></li></ul><p>In addition to following an iterative <a href="https://towardsdatascience.com/the-data-science-process-a19eb7ebc41b">Data Science Process</a> and coding in <a href="https://towardsdatascience.com/top-python-libraries-for-data-science-c226dc74999b">Python</a>, I used libraries <a href="https://numpy.org/doc/stable/user/whatisnumpy.html">numpy</a> for computation, <a href="https://pandas.pydata.org/docs/user_guide/index.html">pandas</a> to manipulate data as <a href="https://pandas.pydata.org/docs/reference/api/pandas.DataFrame.html#pandas.DataFrame">DataFrames</a>, <a href="https://matplotlib.org/3.3.3/tutorials/index.html">matplotlib</a> to visualize player tracking data, and <a href="https://scikit-learn.org/stable/">Scikit-Learn</a> to implement ML algorithm <a href="https://towardsdatascience.com/getting-started-with-xgboost-in-scikit-learn-f69f5f470a97">XGBoost Decision Trees</a>. See my project’s full code <a href="https://github.com/klordi/lordi_nfl_big_data_bowl_2021">here</a>. If I had more time, there are many concepts I would love to continue learning about to utilize.</p><p><strong>2. Spark discussions about the evolving applications of AI &amp; Analytics in the NFL— Game Strategy, Player Health &amp; Safety, Sports Betting.</strong></p><p>The Big Data Bowl engages the analytics community to help innovate the way football is played and coached. I was excited to contribute to this effort!</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/956/1*d6boPHwhqXQpn5KCtyTO8Q.jpeg" /><figcaption>Dec 3, 2017. New England Patriots cornerback Stephon Gilmore knocks down a pass to Buffalo Bills wide receiver Zay Jones. In 2018, <a href="https://www.pff.com/news/pro-top-25-cornerbacks-in-the-nfl-in-2018">Gilmore</a> was the #1 ranked cornerback, and New England shadowed receivers more than any other team. <a href="https://www.pff.com/news/pro-the-nfls-prototypical-defensive-backs-for-each-secondary-position-heading-into-2019">Credit: Timothy T. Ludwig-USA TODAY Sports</a></figcaption></figure><h3>Data Preparation &amp; Exploratory Analysis</h3><p><a href="https://www.datacamp.com/community/tutorials/data-preparation-with-pandas"><strong>Preparing the data</strong></a> is the important first step in order to efficiently and accurately analyze it. I did most of work in the <a href="https://github.com/klordi/lordi_nfl_big_data_bowl_2021/blob/main/DataPrep.ipynb">DataPrep Python file</a>. Luckily, the <a href="https://www.kaggle.com/c/nfl-big-data-bowl-2021/data">datasets</a> for this competition were pretty clean, and .csv files were linked by columns with numerical IDs for game, play, and player. I also did some <a href="https://towardsdatascience.com/exploratory-data-analysis-in-python-c9a77dfa39ce"><strong>Exploratory Data Analysis</strong></a><strong> </strong>in this step. Here is a summary of what I did:</p><ol><li>Read in raw .csv data files using the <a href="https://www.datacamp.com/community/tutorials/data-preparation-with-pandas">pandas library</a>.</li><li>Converted categorical columns (ex. passResult, position) to numerical ones in order to use in exploratory data analysis and ML models.</li><li><a href="https://docs.python.org/3/library/pickle.html#:~:text=%E2%80%9CPickling%E2%80%9D%20is%20the%20process%20whereby,back%20into%20an%20object%20hierarchy.">Pickled the data</a> to make size more manageable and saved as <a href="https://github.com/klordi/lordi_nfl_big_data_bowl_2021/tree/main/Data">new .csv files</a>.</li><li>Joined <a href="https://github.com/klordi/lordi_nfl_big_data_bowl_2021/tree/main/Data">pickled tracking data</a> with player, play, and game data into one file in order to analyze relationships between variables.</li><li>Conducted <a href="https://towardsdatascience.com/exploratory-data-analysis-in-python-c9a77dfa39ce">Exploratory Data Analysis</a> and made a variety of charts such as scatter plots, histograms, and heat maps to understand the content of the 2018 Regular Season NFL Data.</li><li><a href="https://medium.com/@urvashilluniya/why-data-normalization-is-necessary-for-machine-learning-models-681b65a05029">Normalized the data</a> using two transforms: (1) Normalized tracking data to line of scrimmage x = 0. (2) Normalized defender and football position in tracking data to target receiver at (x,y) = (0,0). Normalizing the data helps ensure that values of numeric columns are on a common scale in case any features have different ranges. Among other things I looked into to prepare data for future projects, I read about <a href="https://www.sciencedirect.com/science/article/abs/pii/0305048396000102">impacts of data rescaling, standardization, and normalization</a> on ML.</li></ol><figure><img alt="" src="https://cdn-images-1.medium.com/max/935/1*7Gc7OdVo9ifystXQUxbLcg.png" /><figcaption>Player Tracking Data Visualization: QB Aaron Rodgers passes complete deep left to DeVante Adams pushed out of bounds at DET 9 for 30 yards. Adams was closely covered by Cornerback Darius Slay.</figcaption></figure><h3>Feature Engineering &amp; Graphical Visualizations using Matplotlib</h3><p>Features are inputs to ML algorithms and are usually structured columns in the data. Therefore, I <a href="https://towardsdatascience.com/feature-engineering-for-machine-learning-3a5e293a5114">engineered features</a> that characterize the defense and appended these as columns in my code to help improve the performance of the ML model designed to classify pass result using features characterizing the defense. I also made simple 2D graphical <a href="https://hdsr.mitpress.mit.edu/pub/zok97i7p/release/2#:~:text=The%20main%20goal%20is%20to,modeling%20output%2C%20and%20presenting%20results.">data visualizations</a> in Python’s <a href="https://matplotlib.org/3.3.3/tutorials/index.html">matplotlib</a> library to help see relationships between variables. Here is what I engineered:</p><ul><li><strong>Target Receiver of Pass</strong>: Found by splicing the playDescription field in the form of “(Shotgun) N.Foles pass short right to Z.Ertz to PHI 39 for 2 yards (L.Joyner).” Identifing Zach Ertz as the target receiver and Lamarcus Joyner as his defender</li><li><a href="https://machinelearningmastery.com/distance-measures-for-machine-learning/"><strong>Euclidean Distances</strong></a><strong> (x, y)</strong> between the target receiver, football, and every defender of the field at every point in time</li></ul><p>I wrote a function that creates 3 subplots of the positions of defenders relative to the normalized target receiver using <a href="https://datavizproject.com/data-type/hexagonal-binning/#:~:text=Hexagonal%20binning%20plots%20density,%20rather,the%20area%20of%20the%20hexagons.&amp;text=There%20are%20many%20reasons%20for,2D%20surface%20as%20a%20plane.">Hexagonal Bin Plots</a>. The blue dot is the target receiver. Darker red areas represent a greater density of defenders within that region of the target receiver at the play event pass_arrived, meaning that the football just arrived to the target receiver. In the first three plots, the play result is complete [C] while in the next three, the play result is incomplete [I].</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*gKrFxX9X8mv1JBlXADbS8w.png" /></figure><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*Yffz_mwFWs63f_60H4QpBQ.png" /><figcaption>Legend: Blue = Target receiver of pass; Red = Density of defenders in binned field region; Play Event = Pass_Arrived. C = pass result is complete; I = pass result is incomplete.</figcaption></figure><p>What we can see comparing the figures is that for completions, more defenders tend to be behind the target receiver and the direction of the ball than for incompletions. This makes sense since receivers are more likely to catch the ball when open and do not have a defender in between them and the quarterback (QB).</p><p>Additionally, to better visualize separation between defender, offender, and the football 🏈, I plotted their positions over time and connected them with solid lines to form a triangle that changes size over the course of the play. Blue is the football, green is the target receiver, and red is the closest defender. Their intitial positions is at the normalized line of scrimmage x = 0.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/468/1*8tu63B__p--RsuXpfuF0Qw.png" /><figcaption>Legend: Blue = football; Red = defender; Green = offender. QB Aaron Rodgers passes complete deep left to DeVante Adams pushed out of bounds at DET 9 for 30 yards. Adams was shadowed by Cornerback Darius Slay.</figcaption></figure><p><a href="https://matplotlib.org/3.3.3/tutorials/index.html">Matplotlib</a> is a powerful data visualization library in Python, one of the main <a href="https://towardsdatascience.com/top-programming-languages-for-data-science-in-2020-3425d756e2a7">programming languages for data science</a>. For me, getting good at making 2D graphs in it took a bunch of practice, and I still have lots of room to grow in areas such as customization and style selections.</p><h4>Getting Started with Matplotlib &amp; Pandas</h4><p>Knowing how to manipulate data, create beautiful graphs and visualizations, and <a href="https://www.tableau.com/about/blog/2020/8/importance-data-storytelling-next-decade-data#:~:text=Data%20storytelling%20turns%20data%20from,better%20return%20on%20your%20investment.">data storytelling</a> is important in so many industries —data/ sports analytics, finance, sales, digital media/marketing, you name it — to help us make data-driven decisions and get ideas across. Therefore, learning to code in a language such as Python and trying out the <a href="https://pandas.pydata.org/pandas-docs/stable/user_guide/visualization.html">pandas and matplotlib libaries</a> is a good start. These are examples of useful technical skills to have as computer science skills are in demand in a variety of industries.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/440/1*yyvHuXzK31uwSilq2zYeZg.png" /><figcaption><a href="https://matplotlib.org/1.5.0/examples/pylab_examples/finance_demo.html">Matplotlib example for finance: Stock prices over time</a></figcaption></figure><h4>Try Exploring Other Data Visualization Libraries</h4><p>Matplotlib is great for exploratory data analysis and creating 2D plots but lacks a little bit for formal presentations. Alternatives to matplotlib include <a href="https://towardsdatascience.com/top-9-libraries-for-data-visualization-in-python-and-r-51bdf08e5d54">other libraries in Python and R</a> such as <a href="https://plotly.com/python/">Plotly</a>, <a href="https://ggplot2.tidyverse.org/index.html">ggplot2</a>, and<a href="https://docs.bokeh.org/en/latest/"> Bokeh</a> for more interactive visualizations. <a href="https://towardsdatascience.com/reviewing-python-visualization-packages-fa7fe12e622b">This article</a> is a good start for reading about pros and cons of data visualization libraries.</p><h3>ML Model: XGBoost Trees to Classify Pass Result</h3><h4>Artificial Intelligence (AI) VS Machine Learning (ML)</h4><p>This is one of the longer sections I reflect on, but informative if you are interested in learning more about AI and ML algorithms to apply AI. Check out the <a href="https://www.morningbrew.com/emerging-tech/guides/what-is-ai"><strong>Emerging Tech Brew’s Guide on AI</strong></a> for one of the best explanations I’ve seen. It is no secret that AI is booming in a variety of sectors. According to <a href="https://www.pwc.com/ai2021?utm_source=morning_brew">PWC’s 2020 AI Report</a>, COVID-19 has accelerated investment in AI for 52% of surveyed businesses.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/700/1*frk0Y3Xd-_rRULlzvf4ftQ.png" /><figcaption><a href="https://towardsdatascience.com/artificial-intelligence-vs-machine-learning-vs-deep-learning-2210ba8cc4ac">Towards Data Science: Artificial Intelligence VS Machine Learning VS Deep Learning</a></figcaption></figure><p><strong>ML, a subset of AI,</strong> employs algorithms that enable systems to find patterns in big data to make predictions and draw conclusions. <a href="https://towardsdatascience.com/types-of-machine-learning-algorithms-you-should-know-953a08248861"><strong>Types of ML</strong></a> include deep learning, supervised/unsupervised learning, and reinforcement learning.<strong> ML algorithms/models</strong> within these types include <a href="https://www.freecodecamp.org/news/deep-learning-neural-networks-explained-in-plain-english/">Neural Networks</a>, <a href="https://towardsdatascience.com/decision-trees-explained-3ec41632ceb6">Decision Trees</a>, <a href="https://towardsdatascience.com/naive-bayes-explained-9d2b96f4a9c0">Native Bayes</a>, and <a href="https://towardsdatascience.com/a-beginners-guide-to-q-learning-c3e2a30a653c">Q-Learning</a> just to name a few. Each is better fit <a href="https://scikit-learn.org/stable/tutorial/machine_learning_map/index.html">for certain types of problems</a>. I just touched on different ML algorithms, but I considered each and their use cases for my project.</p><p>Additionally, to learn about advances of ML technology in American football, I did some research. For instance, these articles explore ML to identify Man VS Zone defensive coverage and model QB decision-making, respectively.</p><ul><li><a href="https://arxiv.org/abs/1906.11373">Dutta, R., Ventura, S., Yurko, R. 26 June 2019. “Unsupervised Methods for Identifying Pass Coverage Among Defensive Backs with NFL Player Tracking Data.” Journal of Quantitative Analysis in Sports 16.2 (2020): 143–161.</a></li><li><a href="https://aws.amazon.com/blogs/machine-learning/predicting-defender-trajectories-in-nfls-next-gen-stats/">Cheong, L., Chi, M., Noori, M., Schaefer, M., Tyagi, A., Zeng, X. “Predicting Defender Trajectories in NFL’s Next Gen Stats.” AWS Machine Learning Blog.</a></li></ul><h4>Hardware Requirements &amp; Computation Needed for ML Models</h4><p>ML models require tons of calculations, and regular consumer hardware may not be able to do them efficiently. Training is the most computationally intensive task. Due to having more cores, GPUs have higher <a href="https://en.wikipedia.org/wiki/Parallel_computing">parallelism</a> than CPUs. Therefore, the <a href="https://www.einfochips.com/blog/everything-you-need-to-know-about-hardware-requirements-for-machine-learning/">CPU and GPU</a> faceoff is real.</p><p>For my ML model for the 2021 Big Data Bowl, I implemented <a href="https://towardsdatascience.com/machine-learning-part-18-boosting-algorithms-gradient-boosting-in-python-ef5ae6965be4">Gradient Boosted Decision Trees</a>. Since the NFL data was large yet manageable and the task was a bit more intensive, I decided to use a <a href="https://docs.aws.amazon.com/dlami/latest/devguide/gpu.html">GPU instance on Amazon EC2</a> and ran my code in a <a href="https://docs.aws.amazon.com/dlami/latest/devguide/setup-jupyter.html">Jupyter Notebook Server on AWS</a><em> </em>so that it would run more quickly. Other cloud services to consider are <a href="https://cloud.google.com/gpu">Google Cloud</a> and <a href="https://azure.microsoft.com/en-us/services/machine-learning/">Microsoft Azure</a>. I look forward to gaining more exposure to different cloud services as I work on future projects in the realm of AI.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*y4GKtRaHhLmwjET4X-WJzQ.png" /><figcaption>How Cloud Service <a href="https://aws.amazon.com/nfl/">AWS powers Next Gen Stats</a></figcaption></figure><h4>Choosing an ML Algorithm From So Many: Why I Chose XGBoost Decision Trees For the NFL Big Data Bowl</h4><p>There are many <a href="https://towardsdatascience.com/best-python-libraries-for-machine-learning-and-deep-learning-b0bd40c7e8c">libraries for Machine and Deep Learning in Python</a>. In the past, I’ve utilized <a href="https://keras.io/">Keras</a> and <a href="https://www.tensorflow.org/">Tensorflow</a> to implement Neural Networks and <a href="https://medium.com/bucknell-ai-cogsci/ai-pitch-statistics-learning-from-decision-trees-and-neural-networks-13cea4d1ccc2">Decision Tree</a>s with Sci-Kit Learn.</p><p>In order to decide which ML algorithm to use and how to implement with <a href="https://towardsdatascience.com/whats-the-deal-with-accuracy-precision-recall-and-f1-f5d8b4db1021">high precision and accuracy</a> , I first defined my problem.</p><p><strong>Problem:</strong> Classify pass play result as complete or incomplete given training data that characterizes defensive backs and their relationships to the football and the target receiver in-play.</p><p>This is a <strong>simple classification problem</strong> with a binary outcome (complete or incomplete). My input features to the model are defense-centric since this year’s challenge is to use data to help evaluate defensive performance on pass plays.</p><p>In order to select the proper ML Classification Algorithm, I did some <a href="https://medium.com/@alex.ortner.1982/top-10-binary-classification-algorithms-a-beginners-guide-feeacbd7a3e2">reading</a> and decided to implement<strong> </strong><a href="https://towardsdatascience.com/understanding-gradient-boosting-machines-9be756fe76ab"><strong>gradient boosted decision trees</strong></a> using <a href="https://xgboost.ai/"><strong>XGBoost</strong></a><strong> </strong>(<a href="https://arxiv.org/abs/1603.02754">Chen and Guestrin 2016</a>), an algorithm I’ve heard of for its success in kaggle competitions. The purpose of gradient boosting is to convert weak learning algorithms such as decision trees into strong ones by optimizing a loss function, a measure of how well the model’s coefficients fit the underlying data. XGBoost is popular for classification, and advantages of using it include its <a href="https://www.kdnuggets.com/2017/10/xgboost-concise-technical-overview.html">sparsity awareness</a>, built-in <a href="https://scikit-learn.org/stable/modules/cross_validation.html">cross-validation</a> to avoid overfitting, and many others described <a href="https://towardsdatascience.com/https-medium-com-vishalmorde-xgboost-algorithm-long-she-may-rein-edd9f99be63d">here</a>.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/925/1*E725tgdPQUtJfAD2vpBGPg.jpeg" /><figcaption><a href="https://www.kdnuggets.com/2019/05/xgboost-algorithm.html">KGNuggets: Evolution of tree-based algorithms over the years</a>. Read <a href="https://arxiv.org/pdf/1603.02754.pdf">this paper (Chen and Guestrin 2016 )</a> to learn more in-depth how the XGBoost algorithm works.</figcaption></figure><h4><a href="https://xgboost.readthedocs.io/en/latest/python/python_intro.html">XGBoost Python Package</a> Implementation: Summary of Steps</h4><p>See my full code in Github <a href="https://github.com/klordi/lordi_nfl_big_data_bowl_2021/blob/main/XGBoostModel.ipynb">here</a>. (1) <a href="https://xgboost.readthedocs.io/en/latest/build.html">Installed XGBoost</a>. (2) Input data and features for model as <a href="https://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.DataFrame.html">Pandas Dataframe</a>.(3) Set test data size to 30% and training to 70%. (4) Loaded data into a DMatrix. (5) Set <a href="https://xgboost.readthedocs.io/en/latest/parameter.html">booster parameters</a> — max depth, eta, objective, number of classes. (6) Set number of training iterations. (7) Trained the model. (8) Classified pass result and made predictions from training and test data to output <a href="https://www.analyticsvidhya.com/blog/2020/09/precision-recall-machine-learning/">precision, recall, and accuracy</a>.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/712/1*JUySMw-GuWzEfszaSEE1Yw.jpeg" /><figcaption>Inputs to XGBoost Decision Trees to classify pass result as complete or incomplete at play event of pass arrived.</figcaption></figure><h4>Results</h4><p><strong>Predictions from Training Data: </strong>Precision 96%; Recall 74%; Accuracy 90%</p><p><strong>Predictions from Test Data: </strong>Precision 46%; Recall 39%; Accuracy 79%</p><p><strong>So… how did my XGBoost implementation do? </strong>Even though the model had an accuracy of 79% to classify pass result on test data (which doesn’t seem that awful), the model clearly <a href="https://machinelearningmastery.com/overfitting-and-underfitting-with-machine-learning-algorithms/">overfit</a> the training data. This means that it modeled the training data so well that performance on the test data was negatively impacted. See below for how I would address overfitting next time. It’s okay, I learned from this :).</p><h4>XGBoost Improvements For Next Time:</h4><p>There are a bunch, and I touch on them briefly here:</p><ul><li><a href="https://www.capitalone.com/tech/machine-learning/how-to-control-your-xgboost-model/"><strong>Minimize Overfitting</strong></a><strong> </strong>to more accurately classify test data and pass results. One way is to utilize XGBoost’s built-in <a href="https://xgboost.readthedocs.io/en/latest/python/python_intro.html#early-stopping">early stopping</a>, which works by finding the inflection point where performance on test data starts to decrease and performance on the training data improves as the model begins to overfit.</li><li><strong>Utilize </strong><a href="https://machinelearningmastery.com/evaluate-gradient-boosting-models-xgboost-python/"><strong>k-Fold Cross-Validation</strong></a><strong> </strong>supported in <a href="https://scikit-learn.org/stable/modules/generated/sklearn.model_selection.KFold.html">scikit-learn</a> to measure the performance of XGBoost. It splits data into k-parts and you get k different performance scores able to summarized with a mean and standard deviation of classification accuracy.</li></ul><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*JnRJAWq8eYf_B2mF5tC0kg.png" /><figcaption><a href="http://ethen8181.github.io/machine-learning/model_selection/model_selection.html">Visual: k-Folder Cross Validation to measure model performance</a></figcaption></figure><ul><li><strong>Utilize </strong><a href="https://medium.com/@MohammedS/performance-metrics-for-classification-problems-in-machine-learning-part-i-b085d432082b#:~:text=We%20can%20use%20classification%20performance,primarily%20used%20by%20search%20engines."><strong>ML Evaluation Metrics for Classification Problems</strong></a> such as the Confusion Matrix, F1 Score, AUC-ROC Curve, and Gini Coefficient. For instance, in <a href="https://towardsdatascience.com/understanding-auc-roc-curve-68b2303cc9c5">AUC-ROC Curve</a>, AUC = Area Under the Curve. In context of my project, a higher AUC says that the model can distinguish between completions and incompletions more accurately.</li></ul><h3>Presenting the Results</h3><p>After implementing XGBoost and running out of time before the project was due (lol), I didn’t get to present my results in a visually-appealing or interactive way to tell a more powerful story about the data. However, I explored powerful data visualization libaries methods so that I have these in my toolbox next time.</p><p>Notably, there are many libraries in <a href="https://www.javascript.com/">JavaScript</a>, another top language for data science and web development to help one make beautiful data visualizations using interactive web pages. Some of <a href="https://medium.com/javascript-in-plain-english/best-javascript-data-visualization-libraries-for-2020-15291919a176">Javascript’s top data visualization libraries</a> include <a href="https://d3js.org/?r=btpg">D3.js</a>, <a href="https://developers.google.com/chart/?r=jspe">Google Charts</a>, and <a href="https://ui.toast.com/tui-chart?r=jspe">Toast UI Chart</a>. Outside JavaScript, <a href="https://www.tableau.com/">Tableau</a> is also used heavily by business intelligence professionals.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*TPkF8L9XazgMlIi7zu2y1Q.png" /><figcaption><a href="https://medium.com/@Elijah_Meeks/d3-is-not-a-data-visualization-library-67ba549e8520">D3 is THE Data Visualization Library.</a></figcaption></figure><p>I was also inspired by some of the ways <a href="https://www.kaggle.com/c/nfl-big-data-bowl-2021/discussion/217170">winners of the 2021 Big Data Bowl</a> presented their results visually. I’d explore them if you have time they are soo cool and well done.</p><h3>Discussion: Evolving Applications of AI &amp; Analytics in Sports</h3><h4><a href="https://aws.amazon.com/nfl/#:~:text=NFL%20player%20tracking%2C%20also%20known,charting%20individual%20movements%20within%20inches.">NFL Next Gen Stats &amp; AWS</a></h4><p>As I applied ML in my <a href="https://www.kaggle.com/ktl008/defensive-back-domination-nfl-big-data-bowl-2021/data#Notable-Engineered-Features,-Visualizations,-&amp;-Data-Formatting">2021 Big Data Bowl submission</a>, engineers are applying ML to Next Gen Stats aka Player Tracking Data in order to create next-level game-day stats. Some of the ones we see on prime time football include <a href="https://www.nfl.com/news/next-gen-stats-introduction-to-completion-probability-0ap3000000964655#:~:text=Passes%20traveling%20more%20than%2040,of%20a%20completion%20also%20increases.">completion probability</a> and hopefully new defensive stats generated from this year’s Big Data Bowl. What’s next? <a href="https://aws.amazon.com/nfl/#:~:text=NFL%20player%20tracking%2C%20also%20known,charting%20individual%20movements%20within%20inches.">Here</a> is the NFL/AWS AI Playbook available for download to keep up. AWS also powers other sports and leagues (NHL, NASCAR, and others).</p><h4>Game Strategy for Coaches, Teams, &amp; Players</h4><p>How can coaches, teams, and players benefit from ML insights via Next Gen Stats while preparing for the next week or while in-game? Currently, the <a href="https://www.allthingsdistributed.com/2020/11/how-the-seahawks-are-using-an-aws-data-lake-to-improve-their-game.html">Seattle Seahawks</a> are dubbed the most “tech-progressive and data-driven teams in the NFL” for leveraging AWS cloud and ML services for operational efficiencies and strategic game insights. Through use of a <a href="https://www.allthingsdistributed.com/2020/11/how-the-seahawks-are-using-an-aws-data-lake-to-improve-their-game.html">data lake</a> that stores big data in a serverless architecture, the Seahawks hope to improve talent &amp; acquisition, player health &amp; recovery, and prepare for games. Other teams are currently moving in a similar direction as they figure out how to leverage data and AI for competitive edge. I hope the Philadelphia Eagles are next!</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/780/1*qnvWF7kqS_OuGgtLc4eeLA.jpeg" /><figcaption><a href="https://www.seattletimes.com/business/amazon/amazons-cloud-computing-will-help-seahawks-tackle-data-for-a-competitive-edge/">Amazon’s cloud computing will help Seahawks tackle data for ‘a competitive edge’</a></figcaption></figure><p>Microsoft also has a strong partnership with the NFL and individual teams and provides <a href="https://www.microsoft.com/inculture/sports/nfl-surface-teams/">Microsoft Surface tablets</a>, Surface Sideline Viewing System (SVS) technology, and most recently <a href="https://news.microsoft.com/2020/03/03/microsoft-and-the-nfl-expand-partnership-to-accelerate-digital-transformation-across-the-league/">Microsoft Teams</a> in 2020. However, AWS is the NFL’s official cloud and AI provider. <a href="https://news.microsoft.com/2020/04/16/nba-announces-new-multiyear-partnership-with-microsoft-to-redefine-and-personalize-the-fan-experience/">Microsoft</a> on the other hand became the official AI and laptop provider of the NBA in April 2020 in a new multi-year deal, beating AWS and Google. I wonder what kinds of insights teams will be able to access directly from their surface tablets in real-time due to ML advances as well as utilize to prepare for games in years to come.</p><h4>Player Health &amp; Safety</h4><p>In addition to using data and AI to enhance fan experience, team infrastructure, and stategy of the game, The NFL is also leveraging it to <a href="https://operations.nfl.com/inside-football-ops/players-legends/player-health-safety/">help keep players safe</a>. For example one recent data-driven <a href="https://ftw.usatoday.com/2019/02/2019-super-bowl-kickoff-rules">kickoff rule change</a> came about in 2018, which resulted in <a href="https://www.si.com/nfl/2019/03/01/concussions-decrease-kickoffs-head-injuries-reduced">a 38% reduction in kickoff concussions in 2018</a>. Data during the 2015–17 seasons showed that players had about 4x the risk of concussion at kickoff compared to pass or running plays.</p><p>These data-driven insights about concussions came about through another analytics competition the NFL sponsors called <a href="https://www.nfl.com/causes/1st-and-future/">NFL 1st and Future</a> designed to spur innovation in athlete safety and performance. This year’s data science/AI challenge was one in computer vision to challenge competitors to create ways to detect on-field helmet impacts. See more information about the 2021 winning submissions <a href="https://www.nfl.com/playerhealthandsafety/equipment-and-innovation/1st-and-future/winners-named-for-nfl-s-sixth-annual-1st-and-future-pitch-competition-powered-by">here</a>.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/512/1*YnCZrjc7tGXEconEPK8rHA.jpeg" /><figcaption><a href="https://www.nfl.com/causes/1st-and-future/past-winners">Past Winners: NFL 1st &amp; Future Analytics Competition</a></figcaption></figure><h4>Sports Betting</h4><p>This is a whole another topic, but an important one as a record 7.6 million Americans were expected to <a href="https://www.foxbusiness.com/sports/draftkings-fanduel-issues-super-bowl-lv-kickoff">bet online for Super Bowl LV</a> according to the American Gambling Association. This is 63% increase from last year, which is largely due to the increased adoption of legal betting in United States. However, about an hour before kickoff, customers could not access their online Sportsbooks as the servers of DraftKings and FanDuel could not handle the demand. It’ll be interesting to see the potential advances and uses of ML in the world in sports betting in years to come and consider the potential ethical implications of this.</p><h3>My Final Reflection on this Reflection</h3><p>I just covered a lot, ranging from my technical data science process to discussions about AI/ML in sports, but had so much fun learning through writing. I hope that you enjoyed reading!</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=1d515b2e54c1" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[AI & Pitch Statistics: Learning from Decision Trees and Neural Networks]]></title>
            <link>https://medium.com/bucknell-ai-cogsci/ai-pitch-statistics-learning-from-decision-trees-and-neural-networks-13cea4d1ccc2?source=rss-1f00722da339------2</link>
            <guid isPermaLink="false">https://medium.com/p/13cea4d1ccc2</guid>
            <category><![CDATA[machine-learning]]></category>
            <category><![CDATA[csci379]]></category>
            <category><![CDATA[neural-net]]></category>
            <category><![CDATA[decision-tree-classifier]]></category>
            <category><![CDATA[analytics]]></category>
            <dc:creator><![CDATA[Katherine Lordi]]></dc:creator>
            <pubDate>Fri, 08 Nov 2019 04:01:49 GMT</pubDate>
            <atom:updated>2019-11-14T01:42:48.277Z</atom:updated>
            <content:encoded><![CDATA[<figure><img alt="" src="https://cdn-images-1.medium.com/max/800/0*pf1XYReFRF57KMhM" /><figcaption><a href="https://gumgum.com/insights/the-visionary/features/moneyball-3-0-how-visual-data-is-supercharging-sabermetrics-in-sports">Moneyball 3.0: How Visual Data Is Supercharging Sabermetrics In Sports</a></figcaption></figure><p>By:<a href="https://medium.com/@ktl008"> Katherine Lordi</a>, <a href="https://medium.com/@ebm009">Eli Mauskopf</a>, &amp; <a href="https://medium.com/@jas129_250">Jazmyn Stokes</a></p><p>We implemented a <a href="https://www.datacamp.com/community/tutorials/decision-tree-classification-python">Decision Tree</a> and an <a href="http://neuralnetworksanddeeplearning.com/">Artificial Neural Network</a> to classify pitches as swing or no swing and ball or strike (using 1’s and 0’s) in order to help batters and umpires. Specifically, we used the <a href="https://scikit-learn.org/stable/modules/tree.html">Python Scikit-Learn package</a> and <a href="https://keras.io/">Python Keras API</a>. In the process, we applied some skills in data science and learned more about these Classification Algorithms. Here’s how we got there!</p><h3>Our Motivation</h3><p>In the exploration of theories and methods related to Artificial Intelligence (AI) and Cognitive Science, our team (Katherine and Eli being MLB fans and Jazmyn a D1 softball player) wondered how AI can change the game of baseball due to all of the quantifiable statistics available. For example, sports analytics can provide a team with competitive advantage. <em>How can we use data and AI to help batters improve their game?</em></p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/0*sngr7teak-1Ghu_1.jpg" /></figure><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/0*QarJ_HQ3bKtlZlCg.jpg" /><figcaption>The desire for robot umpires like TrackMan (pictured on right) increased in light of the 2019 World Series between the Washington Nationals and the Houston Astros.</figcaption></figure><blockquote>“C’mon, Lance!” he shouted from the bench. “It’s the World Series! Wake up!” — Washington Manager Dave Martinez</blockquote><p>Additionally, the desire for robot umpires has increased in light of the <a href="https://abcnews.go.com/Sports/wireStory/pitch-series-call-louder-robot-umps-66602986">2019 World Series</a>. In Game 5, home plate umpire Lance Barksdale called Gerrit Cole’s fastball to Victor Robles as strike three, but the 40,000 in the bleachers did not agree. Robles was upset about the call but noted that “we all make mistakes,” which is part of being human. Umpires have a need for assistance to make accurate calls (especially during high stake games), which is being addressed by new technologies such as TrackMan. <em>How can we use AI to help umpires make more accurate pitch calls?</em></p><h3>Our Dataset: MLB Pitch Statistics (2015–2018)</h3><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*LR1uW-kvMGMCQKzBHLOOEA.png" /><figcaption>See the dataset on Kaggle <a href="https://www.kaggle.com/pschale/mlb-pitch-data-20152018#pitches.csv">here</a>!</figcaption></figure><p>While investigating our motivating questions, we looked for informative datasets with historical baseball statistics. We found a dataset on Kaggle that consists of scraped <a href="https://www.kaggle.com/pschale/mlb-pitch-data-20152018#pitches.csv">MLB Pitch Statistics 2015–2018</a>. The dataset provides 40 factors about pitches as columns such as pitch type, outcome, position, velocity, runner placement, spin, break angle, and more. Each row is one pitch, and each year of data has over 700,000 pitches.</p><h3>The Problem: Pitch Classification</h3><p>After conducting research and finding MLB Pitch Data for 2015 to 2018, we narrowed our scope to the following classification problems:</p><ol><li><strong><em>Applications of AI to Help Batters</em>:</strong> Determine what kind of ball a batter should swing at in order to increase batting average and decrease strikeouts by classifying pitches as swing or no swing.</li><li><strong><em>Applications of AI to Help Improve Accuracy of Called Pitches: </em></strong>Help improve the accuracy of called pitches as a ball or strike.</li></ol><h3><strong>Classification Algorithms Explored</strong></h3><p>To explore our pitch classification problem, we explored Artificial Neural Networks and Decision Trees, two of the most popular classification algorithms. We also sought to learn about their strengths, weaknesses, and differences. While Artificial Neural Networks (ANN) are biologically-inspired simulations of the neural networks of human brains, Decision Trees create a model that predicts the value of the target variable (leaves) using decision rules and observations (branches).</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/874/1*CEXufa9cpynWCNQFvBY7KA.jpeg" /><figcaption><a href="https://towardsdatascience.com/building-a-deep-learning-model-using-keras-1548ca149d37">Neural Network</a></figcaption></figure><h4>Neural Networks VS Decision Trees</h4><p>Black box machine learning models such as Neural Networks are more difficult to interpret and explain while white box models such as Decision Trees have more explainable results by boolean logic. However, there are tradeoffs. Black box models provide for greater accuracy than white box models. Both are flexible algorithms that can handle nonlinear data and interactions between variables, but Decision Trees are more compatible with classification problems while Neural Networks work better with patterns. Additionally, Decision Trees train faster on large amounts of data.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/541/0*rGs7cUDkeeN-rBaF.png" /><figcaption><a href="https://www.datacamp.com/community/tutorials/decision-tree-classification-python">Decision Tree</a></figcaption></figure><h3>Implementation</h3><p>We implemented our <a href="https://www.datacamp.com/community/tutorials/decision-tree-classification-python">Decision Tree</a> using the <a href="https://scikit-learn.org/stable/modules/tree.html">Python Scikit-Learn package</a> and our Artificial Neural Network using the the <a href="https://keras.io/">Python Keras API</a> to solve our pitch classification problem. We have some experience using Keras and wished to apply it to another type of problem.</p><p>First, we created dictionaries mapping the code (pitch outcomes) and zone (location of pitch in strike zone) of each pitch to 0 (do NOT swing / ball) and 1 (swing / string). We did this because inputs to the Decision Tree and Neural Network need to be integers. Additionally, it simplifies our categories for classifying pitches to a binary output.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*DUIvWacix7fiwlESD5UIQg.jpeg" /><figcaption>See MLB Pitch Statistics 2015–2018: Code = Outcome of Pitch, Zone = Location of Pitch in Strike Zone</figcaption></figure><h4><em>Python Keras Artificial Neural Network</em></h4><p>Our Neural Network implementation is inspired by <a href="https://machinelearningmastery.com/multi-class-classification-tutorial-keras-deep-learning-library/">this article</a>, which explains how to construct a Neural Network to classify types of iris flowers. We modified the implementation to consider code and zone as our target outputs and created unique input arrays to specify which inputs to use on a test run. Next, we tweaked the baseline model to have 3 layers with varying input layer dimensions depending on how many columns of pitch statistics we use as input. We used a relu <a href="https://towardsdatascience.com/activation-functions-neural-networks-1cbd9f8d91d6">activation function</a> for the hidden layer and a softmax function for the output in order to keep the output score between 0 and 1. For back propagation, we used <a href="https://towardsdatascience.com/adam-latest-trends-in-deep-learning-optimization-6be9a291375c">Adam gradient descent optimization</a> with a logarithmic loss function. To evaluate our model, we used k-fold cross validation, which constructs 10 of our models and evaluates how well they predict our target output. After running our 10-fold cross validation procedure, we printed the average of all folds, standard deviation, and accuracy.</p><h4><em>Python Scikit-Learn Decision Tree</em></h4><p>Our Decision Tree implementation is inspired by <a href="https://www.datacamp.com/community/tutorials/decision-tree-classification-python">this article</a>, which explains how to to build a Decision Tree Classifier using Python Scikit-learn package. First, we split the MLB Pitch Statistics 2015–2018 dataset into csv files by year using a Python script in order to train our model one year and make predictions on another year. After loading in the pitch data an creating output files, we created the Decision Tree classifier object, trained the Decision Tree classifier, and set the predicted output of the classifier. Finally, we printed the accuracy of the model, which answers the question, “How does the decision tree output to the actual output in the dataset?” For instance, we compare the decision tree making a prediction on code (1 is swing and 0 is no swing) to the actual code column in the dataset.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/985/1*xtAPHIPReIYm6xqAZoif3Q.png" /><figcaption>Decision Tree Algorithm</figcaption></figure><h3>Results &amp; Analysis</h3><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*otF5t7YyEG2zNqZC0nMYSA.png" /><figcaption>Example runs that compares the accuracy of Neural Network to accuracy of Decision Tree for different input cases</figcaption></figure><p>We tried input cases ranging from the pitch’s initial position in the pitcher’s hand to as many relevant pitch statistics as possible. After analyzing the data for input cases we tried, we had some observations:</p><ul><li>Given the same number of input pitch statistics, we cannot determine if the Decision Tree performs better than the Neural Network. This is because we trained the Decision Tree on 100,000 pitches and the Neural Network on 200–1000 pitches due to runtime. Since we did not train the Neural Network on the same amount of data as the Decision Tree, we are not sure which one did better!</li><li>Pitch statistics more related to the pitch’s placement in the strike zone as inputs had higher accuracies for the both the Decision Tree and the Neural Network when predicting code and zone.</li><li>For the Decision Tree, input cases consisting of more pitch statistics had greater accuracy.</li></ul><h3>Challenges Faced</h3><p>With some of us being new to the world of AI and data science, we faced some challenges along the way and had to adapt and be creative. One challenge that we faced was the size of the <a href="https://www.kaggle.com/pschale/mlb-pitch-data-20152018#pitches.csv">MLB Pitch Statistics dataset</a>, which contaminated over 700,000 pitches per year. While our Decision Tree Implementation ran on all the rows in a matter of seconds, the Keras Neural Network runtime took about four minutes for 1,000 rows of pitch training data. Working with the Keras Neural Network was also challenging since it is a black box model.</p><p>Another challenge that we faced was assessing the impact of human error in baseball as reflected in the pitch statistics since batters make mistakes. For example, some pitches that the batter should not have swung at based on its location in the strike zone were actually swung at, which is reflected by the code column. Therefore, we grappled with the accuracy of our Decision Tree and Neural Network and thought about the meaning of the output. Lastly, we had to meticulously consider input cases to train our models and identify meaningful test cases that provide value to batters and umpires.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/0*_tgFVwPU9Bf6rqVr" /><figcaption>Washington Nationals — World Series 2019 Champions</figcaption></figure><h3>Conclusions &amp; Reflections</h3><p>In this project, our team explored AI’s role in sports analytics and baseball, found a dataset of pitch statistics from 2015–2018, and used this dataset to classify pitches as a swing or no swing to help batters and as ball or strike to help improve the accuracy of an umpire’s calls. We implemented a Keras Neural Network and Decision Tree in Python, and through our implementation and results analysis, we saw that AI models are not perfect and are limited by the model setup and the data inputted to them. One future consideration is to add more hidden layers to the Neural Network, which may help improve its accuracy and convergence. Additionally, in the future, we will ensure to train the Neural Network on more pitches to improve its ability to classify pitches given variation of input data.</p><p>Therefore, in the realm of baseball, which is played by humans and has so many human factors that can not yet be fully quantified, AI is more likely to aid rather than replace. In baseball, AI is currently helping umpires, and there are no plans to fully replace them. This ties to some exploration of ethical implications of AI and baseball such as AI’s role in the sports industry and sports betting.</p><p>See our programs and data <a href="https://gitlab.bucknell.edu/jas129/csci379-midterm">here</a>!</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=13cea4d1ccc2" width="1" height="1" alt=""><hr><p><a href="https://medium.com/bucknell-ai-cogsci/ai-pitch-statistics-learning-from-decision-trees-and-neural-networks-13cea4d1ccc2">AI &amp; Pitch Statistics: Learning from Decision Trees and Neural Networks</a> was originally published in <a href="https://medium.com/bucknell-ai-cogsci">Bucknell AI &amp; CogSci</a> on Medium, where people are continuing the conversation by highlighting and responding to this story.</p>]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[My Human-Computer Interaction Design Manifesto]]></title>
            <link>https://klordihavemercy.medium.com/my-human-computer-interaction-design-manifesto-f19e2108ad6d?source=rss-1f00722da339------2</link>
            <guid isPermaLink="false">https://medium.com/p/f19e2108ad6d</guid>
            <category><![CDATA[design]]></category>
            <category><![CDATA[design-process]]></category>
            <category><![CDATA[ux-design]]></category>
            <category><![CDATA[design-thinking]]></category>
            <category><![CDATA[hci]]></category>
            <dc:creator><![CDATA[Katherine Lordi]]></dc:creator>
            <pubDate>Sat, 04 May 2019 06:08:15 GMT</pubDate>
            <atom:updated>2021-04-29T18:33:06.967Z</atom:updated>
            <content:encoded><![CDATA[<h4>My Design Philosophy</h4><p>[ I took some time to revise + edit + clean up this manifesto on 4/28/2021 (2 years later :) to make it less wordy and a bit more readable ]</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/0*h50eW3ydY2pJXAz0" /><figcaption>5 key points that make up my design philosophy. Paper Prototype :)</figcaption></figure><h3><strong>Introduction</strong></h3><p>During my time as a student at Bucknell University majoring in computer science &amp; engineering and management, I’ve immersed myself in software development, data analytics, engineering consulting, and interdisciplinary teamwork. In each of these experiences, I’ve seen how the <strong>design process</strong> and <strong>human-centered design</strong> play an integral role to develop successful products and outcomes that are actually useful for people.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/586/1*sExFD-hD-cB0khKKvXkVGw.png" /><figcaption>I work as a student engineering consultant at the Bucknell SBDC and participated in Interdisciplinary Senior Design. Both of these are client-facing experiences with a huge design component. Read <a href="https://www.dailyitem.com/news/local_news/bucknell-student-engineers-get-experience-with-corporate-heavy-hitters/article_dd53b9c5-68b9-5b3a-97e0-69686a15eb27.html">here</a> for more info about Bucknell’s senior design capstone projects!</figcaption></figure><p>I decided to take Human-Computer Interaction for its interdisciplinary nature, focus on the study of people and different technologies, and my desire to learn about human-centered design and apply what I learn to my own projects.<em> I want to build things that actually solve meaningful problems and that people actually like and use!</em></p><p>In HCI, I had the opportunity to work on multiple teams to design for a variety of modalities such as mobile application interfaces, data visualizations, 3D user interfaces, and aspirational uses of virtual reality. Working with and learning from my teammates while following the human-centered design process was extremely fun and rewarding.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/382/0*YI_vxMQqR7N5_Zu9" /><figcaption>The Iterative Human-Centered Design Process</figcaption></figure><p>Collectively, all the design sprints helped shape my design philosophy. There are countless aspects of human-centered design depending on the technology used and who and what is being designed. However, the following 5 key points make up my own<strong> personal design philosophy</strong> because I have found them to be so integral to the success of a project. I will use them in every future design process!</p><h4><strong>1. Understand The Real Problem</strong></h4><h4><strong>2. Understand Who You Are Designing For</strong></h4><h4><strong>3. Define the Design Goal Early On (As Early As Possible!)</strong></h4><h4><strong>4. Brainstorm with the Design Goal at the Forefront</strong></h4><h4><strong>5. Work Iteratively and Obtain User Feedback</strong></h4><h3>Understand the Real Problem</h3><p>Don Norman’s “The Design of Everyday Things” discusses how it is often easy to see surface level problems and never actually dig deeper to address the real, underlying causes. According to Norman, discovering what the root issues are before designing a solution is extremely useful in Human-Centered Design (HCD) in order to develop products that fit the <strong>needs and capabilities of people</strong> and are <strong>used by people</strong>.</p><p>Additionally, in Andy Ko’s book<a href="http://faculty.washington.edu/ajko/books/design-methods/index.html"> Design Methods</a> and in the chapter <a href="http://faculty.washington.edu/ajko/books/design-methods/how-to-understand-problems.html">How to Understand Problems</a>, Ko communicates that it is crucial to understand as many causes to the problem as possible in order to have a clear understanding of what a problem is. Through the design sprints, I have seen how impactful solutions are specific to problems. Therefore, understanding the root problem makes up the first step in my personal design philosophy.</p><h4><em>Example in the Design for Others Modality: Library App Redesign</em></h4><p>In the <a href="https://medium.com/@ktl008/boom-library-app-redesign-ad7186e5f443">Design for Others</a> sprint, my team and I created a <a href="https://xd.adobe.com/view/15a6ed10-6017-4796-79b4-3322a633a5d6-6397/">prototype</a> in <a href="https://www.adobe.com/products/xd.html?sdid=12B9F15S&amp;mv=Search&amp;ef_id=EAIaIQobChMI1a7c0MeE4gIVBobICh3kngmoEAAYASAAEgIlUvD_BwE:G:s&amp;s_kwcid=AL!3085!3!315233774112!e!!g!!adobe%20xd">Adobe XD</a> for the <a href="http://unioncountylibraries.org/">Union County Library System</a> Mobile App and were tasked to <strong>design specifically for Baby Boomers</strong>. Our goal was to improve the current mobile website interface through a library app redesign. Through the process of <strong>need finding</strong>, we were able to identify key design objectives to focus on for the redesigned mobile site.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/188/0*N_r8XFaw2uDDyzbC" /><figcaption>Screenshot of the old Union County Library System mobile website</figcaption></figure><p>Our team identified pain points such as complicated layout, confusing organization and navigation, and disorganized content to describe the root problem with the current site. Understanding the problem came in handy while defining design objectives and conducting user research on the baby boomers to make informed design decisions regarding informational and visual design. Ultimately, we created a bit sleeker of a mobile interface aimed be experiential, simple, colorful, and readable.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/0*lMnLrMvpPmGog8XK" /></figure><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/0*p-bDc6cv9-VyVag3" /><figcaption>Screenshots of select screen of my team’s final prototype in Adobe XD for the Design For Others Sprint: a mobile application interface for the Union County Library System. This was our first design modality, so looking back, I can see that it can use much more iterating and improvement :)!</figcaption></figure><h3><strong>Understand Who You Are Designing For</strong></h3><p>This is the second step of my personal design philosophy / design manifesto. According to Andy Ko in <a href="http://faculty.washington.edu/ajko/books/design-methods/how-to-understand-problems.html">How to Understand Problems</a>, there is no such thing as the “average user” because everyone’s problems are personal and have different causes and consequences. Every single product and solution out there in the market meets some person’s needs while failing to do the same for others. Therefore, Ko mentions that designers needs to identify a spectrum of needs before deciding <strong>who</strong> to optimize for.</p><p>User research plays a huge role in coming up with this spectrum, and forms of user research include direct methods such as surveys and interviews and indirect methods such as observation and research. Through interpretation and synthesis of data, designers derive goals that people wish to achieve and identify the users to develop and design for.</p><h4><em>Design for Others: Library App Redesign</em></h4><p>In the <a href="https://medium.com/@ktl008/boom-library-app-redesign-ad7186e5f443">Design For Others</a> sprint, my team and I were assigned ‘elderly adults’ as our user group to redesign the Union County Library mobile app. Upon conducting some user research to further understanding this demographic, we decided to call them ‘baby boomers’ rather than elderly adults because of how limiting this label can be. We focused on research in the areas of informational design (what content to present and emphasize for boomers, how to navigate the app, and information hierarchy) and visual design (color schemes, font, design patterns). For example, after collecting primary insights and research on baby boomers, we created and tailored a mood board towards the baby boomer concept and made visual design decisions including color choices such as Facebook blue and Campbell Soup red and contrasting color choices for the mobile app.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/901/0*5OwZa1zEEo9eDaYr" /><figcaption>Mood Board for the Boomers to inform visual design of the mobile app prototype of the Union County Library System formulated based on user research</figcaption></figure><p>The <strong>Double-Diamond Mode</strong>l describes two phases of design and the first two key points I mention according to Norman: Understand the Real Problem and Understand Who You Are Designing For. To actually do these two activities, the iterative cycle of Human-Centered Design is needed.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1000/1*zsjTyLFONs-_sHk4rFO9BQ.png" /><figcaption>The Double-Diamond Model</figcaption></figure><h3><strong>Define the Design Goal Early (As Early as Possible!)</strong></h3><p>Defining the design goal or design objectives as early as possible is the third key point of my design philosophy because <strong>without having a clearly defined goal in mind, much of the rest of the design process is left unguided</strong>. This is the logical next step after understanding the real/root problem and understanding the users to design and optimize for.</p><h4>Failing Forward with our Design Goals… VR for Mindful Guided Meditation</h4><p>For example, in the<a href="https://medium.com/@ktl008/guided-mindful-meditation-an-aspirational-use-of-virtual-reality-48ed488993df"> Design for the Future</a> sprint, my team and I originally found ourselves brainstorming ideas with little success since we did not define our design goal first, which led to ideas out of the scope of our technological capabilities for the project timeline. For example, we brainstormed ideas that involved the leap motion in conjunction with virtual reality such as “virtual reality coloring” without first exploring our tech capabilities using <a href="https://aframe.io/">A-frame</a> and <a href="https://vr.google.com/cardboard/">Google cardboard</a>. Additionally, some of the ideas we brainstormed were more gamified than therapeutic such as “whack a mole” and darts, which was not our original thought for an aspirational use of virtual reality.</p><p>After our failed preliminary round of brainstorming, my team and I identified our design goal that to us, represents a truly aspirational use of VR and began another round of ideation and brainstorming, in which we narrowed down on designing a VR for mindful guided meditation.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/290/0*GzgxiEYvEBfOZjvB" /><figcaption>Meditating in a VR</figcaption></figure><p><strong>Design Goal for Design for the Future: </strong>To create an immersive VR that improves the daily life of people by positively impacting their health and wellness</p><p>Defining the design goal early on and my team’s experience of failing forward after not doing so at first in the <a href="https://medium.com/@ktl008/guided-mindful-meditation-an-aspirational-use-of-virtual-reality-48ed488993df">Design for the Future</a> sprint segways into the next key point in my design philosophy, the importance of smart brainstorming.</p><h3><strong>Brainstorm with the Design Goal at the Forefront</strong></h3><p>Here are examples of how brainstorming with a purpose after defining the design goal led to successful outcomes within the design sprints!</p><h4><em>Design for Fun/Expression: Tap Tap Revolution</em></h4><p>In the <a href="https://medium.com/@ktl008/dance-with-your-hands-with-tap-tap-revolution-31c0f02f35d7">Design for Fun/Expression</a> sprint, the design goal was given to design a 3D user interface that prioritizes fun and expression and simply maximizes the enjoyment that people have using our product. Having this well-defined design goal in mind truly guided our brainstorming and ideation process effectively.</p><p>For example, while choosing the game, keeping fun in mind, and through <a href="https://en.wikipedia.org/wiki/Wizard_of_Oz_experiment">Wizard-of-Oz testing</a> of the <a href="http://slither.io/">Slither.io</a> game idea, we decided to pursue games involving more interactive hand gestures such as Frogger and Flash Flash Revolution. Thus, <a href="https://www.youtube.com/watch?v=br0iUxajNDI">“Tap Tap Revolution”</a> was born.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/750/0*QTwwSDySVNamEBdS" /><figcaption>Wizard-of-Oz testing for Slither.io game. User clenches her fist to indicate a boost in speed.</figcaption></figure><h4><em>Design for Clear Communication and Persuasion: Visualizing Hate Crimes in the USA</em></h4><p>In the design sprint for designing for clear communication and persuasion, defining clear design goals for each type of data visualization using a common dataset (<a href="https://ucr.fbi.gov/hate-crime">FBI Hate Crime Statistics</a>) helped my team find success while brainstorming, sketching, and prototyping in <a href="https://public.tableau.com/profile/judy5625#!/vizhome/shared/HNHMSHGH3">Tableau</a>. Throughout the design process we kept in mind that some <a href="http://socviz.co/lookatdata.html">data visualizations</a> are better than others depending on their purpose due to how visual perception leverages unique pathways in our brains. Through the process of filtering and categorizing sketches in the <a href="http://fds.design/">Five Design-Sheet Process</a>, my team and I categorized charts/graphs/sketches by which data visualization they best belong- clear communication or persuasion.</p><h3><strong>Work Iteratively and Obtain User Feedback</strong></h3><p>The final of the key points that I want to touch upon is the importance of obtaining user feedback throughout multiple stages in the design process and iteratively prototyping. Obtaining user feedback at many points throughout the process ensures the creation of a final product that best meets user needs, desires, and capabilities.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/838/0*yC6sPlZg1fa0ETSr" /><figcaption>User Testing different headphones and headpieces for virtual reality for the Design for the Future sprint</figcaption></figure><p>For example, in the <a href="https://medium.com/@ktl008/guided-mindful-meditation-an-aspirational-use-of-virtual-reality-48ed488993df">Design for the Future</a> sprint in which my team and I created an aspirational meditative virtual reality, we asked users for feedback during class demos in order to make design decisions for our final product. This user feedback guided design choices for ambiance and scenery and answered questions such as “What environments do you prefer to meditate in?” Additionally, we did formative testing with the equipment (VR head piece and headphones) to ensure that it was comfortable and provided a relaxing environment for meditation. Keeping these important design considerations in mind during user testing helped us create a successful final product.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/760/0*waXf9A4g6lUxGA0z" /><figcaption>Considerations for designing a meditative experience in a VR environment that our team sought user feedback on iteratively throughout the prototyping process</figcaption></figure><h3>Conclusion</h3><p>Reflecting on the semester and thinking about everything that I learned and experienced, I truly realize the power of a good design process for designing meaningful solutions <strong>for users</strong><em>. </em>HCI involves interdisciplinary thinking, the study of different people and technologies, and human-centered design approaches. Through going through four design sprints and focusing on unique design goals for each, I grew as a problem solver, designer, and software developer. I look forward to carrying personal design philosophy with me into every future project to keep users as #1.</p><p>Thank you for reading!</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=f19e2108ad6d" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Guided Mindful Meditation: An Aspirational Use of Virtual Reality]]></title>
            <link>https://klordihavemercy.medium.com/guided-mindful-meditation-an-aspirational-use-of-virtual-reality-48ed488993df?source=rss-1f00722da339------2</link>
            <guid isPermaLink="false">https://medium.com/p/48ed488993df</guid>
            <category><![CDATA[meditation]]></category>
            <category><![CDATA[vr-experiences]]></category>
            <category><![CDATA[hci]]></category>
            <category><![CDATA[virtual-reality]]></category>
            <category><![CDATA[vr]]></category>
            <dc:creator><![CDATA[Katherine Lordi]]></dc:creator>
            <pubDate>Fri, 26 Apr 2019 04:02:17 GMT</pubDate>
            <atom:updated>2019-04-26T04:02:17.858Z</atom:updated>
            <content:encoded><![CDATA[<h4>By: <a href="https://medium.com/u/e69211e5a0ad">Casey Friend</a>, <a href="https://medium.com/u/f3ac20d66b17">John Hunt</a>, <a href="https://medium.com/u/1f00722da339">Katherine Lordi</a>, <a href="https://medium.com/u/9641c3b4cd18">Judy Peng</a></h4><h3><strong>Introducing a VR For Guided Mindful Meditation</strong></h3><p>What is an aspirational use of VR that makes a profound and meaningful impact on users? Our team came together in order to design something that embodies what we collectively think VR should be using <a href="https://aframe.io/">A-Frame</a> and the <a href="https://vr.google.com/cardboard/">Google cardboard</a>. Following our design process, building, and user testing in this design sprint, our team is happy to introduce our VR for Guided Mindful Meditation.</p><iframe src="https://cdn.embedly.com/widgets/media.html?src=https%3A%2F%2Fwww.youtube.com%2Fembed%2FhiiqnFaiAnU%3Ffeature%3Doembed&amp;url=http%3A%2F%2Fwww.youtube.com%2Fwatch%3Fv%3DhiiqnFaiAnU&amp;image=https%3A%2F%2Fi.ytimg.com%2Fvi%2FhiiqnFaiAnU%2Fhqdefault.jpg&amp;key=a19fcc184b9711e1b4764040d3dc5c07&amp;type=text%2Fhtml&amp;schema=youtube" width="854" height="480" frameborder="0" scrolling="no"><a href="https://medium.com/media/2a1e056bee09235002acf894f3b63c31/href">https://medium.com/media/2a1e056bee09235002acf894f3b63c31/href</a></iframe><p><em>Our VR for Guided Mindful Meditation is a way to enter a new environment and listen to a guided voice that encourages mindfulness and relaxation as a break from the stressors of everyday life.</em></p><p>Here is our <a href="https://glitch.com/~mobile-vr-iteration3">Project Repo</a> and <a href="https://mobile-vr-iteration3.glitch.me/">App</a>! (Note: sounds could not work properly in IOS due to specifics of the system.)</p><h3><strong>The Design Process</strong></h3><p>Our team came together because of the balance of our technical and design skills and our interest in innovating on something that helps make one a better, healthier version of themself. Therefore, for the creation of our final VR product, our team identified our design goal that to us, represents a truly aspirational use of VR:</p><h4><strong>Our Design Goal</strong></h4><p><strong><em>To create an immersive VR that improves the daily life of people by positively impacting their health and wellness.</em></strong></p><p>Through brainstorming &amp; ideation, prototyping, and formative testing phases of our design process, our team made sought to make design decisions that aligns with this design goal. We also greatly considered the challenges of and design concepts involved in making the VR immersive in order to make our design impactful and captivating for users.</p><h3><strong>Brainstorming &amp; Ideation for Aspirational Uses of VR</strong></h3><h4><strong>Finding Inspiration</strong></h4><p>After collectively defining our design goal, we started off the design process by brainstorming as many potential ideas as possible. We generated our ideas based on research and readings we have come across that introduce unique approaches to VR and how VR is solving challenging problems that impact people across the globe in positive ways. These inspirational uses of VR range from <a href="https://www.wired.com/story/opioids-havent-solved-chronic-pain-maybe-virtual-reality-can/">chronic pain</a> and the <a href="https://www.wired.com/story/opioids-havent-solved-chronic-pain-maybe-virtual-reality-can/">opioid epidemic</a> to<a href="https://www.theguardian.com/technology/2017/oct/07/virtual-reality-acrophobia-paranoia-fear-of-flying-ptsd-depression-mental-health"> therapeutic treatments</a> such as <a href="https://arvrjourney.com/vr-neurofeedback-a-new-drug-free-treatment-for-mental-disorders-f721f652f159">neurofeedback</a> for mental disorders and treatments for PTSD. Some of these readings that have served as inspiration are linked below.</p><h4><strong>Brainstorming &amp; Arriving at Guided, Mindful Meditation in VR</strong></h4><p>Here is a collection of ideas that our team brainstormed.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/0*6RN_j6d2dVPcT5Vn" /><figcaption>Preliminary brainstorming</figcaption></figure><p>We thought about possible ways to implement a VR experience as well as strengths and weaknesses of each idea while keeping our design goal and an immersive VR experience at the forefront.</p><p><strong><em>Designing VR for People With Disability: </em></strong>The idea at the forefront of each of our minds was designing for disability and creating a VR that can potentially help people with disabilities with their treatments. We considered use cases such as ADHD, dementia, PTSD, and physical disabilities. However, after discussing as a team, we realized that an important component for building a successful VR to design for helping those with disabilities involves extensive research and expertise of potential use cases of techniques of coping and recovery. Additionally, it would be useful to conduct multiple interviews with individuals who live with disabilities and experts in the field with an empathetic lens. We kept this idea in our minds as we explored others.</p><p><strong><em>Designing VR for Accessibility: </em></strong>Another ideas was a VR application that allows people to experience need for accessibility. We found inspiration for this idea from our HCI class, in which we did an <a href="https://www.google.com/maps/d/u/0/edit?mid=13b0g6_V38N6N2Lo1cVV0qU5032N7Oyq5&amp;ll=40.95572121703872%2C-76.88281275833702&amp;z=16">activity</a> in which we identified problems with accessibility on Bucknell’s campus. However, considering that we want users to use our VR while standing in place or seated, we realized that it would be difficult to build a truly immersive experience.</p><p><strong><em>Designing VR for Simulations:</em></strong><em> </em>Along with the idea for designing a VR app for accessibility, we also had an idea to make a VR simulator that allows people to experience what it is like to have a disability. Rather than designing for helping the recovery of those with disabilities, the primary concept was for people to be able to empathize with living with a disability. For example, one idea that we came up with was looking through a VR simulator in order to experience what it is like to be color blind.</p><p>While brainstorming, we ran into a couple of roadblocks. First of all, since none us on our team actually have a disability, we would have had to consult many sources and interview people with different disabilities to ensure that what we create is true to the experiences of those living with a disability. The second roadblock was that our app would not be as interactive and immersive as we would like it to be since we envision the user sitting or standing in place. Balancing physical controls, such as controlling a wheelchair, and creating an environment for the user to interact, would prove to be a pretty immense scope. Therefore, we considered other aspirational VR ideas such as designing for therapy.</p><p><strong><em>Designing VR for Therapy:</em></strong><em> </em>Another potential option that we greatly considered was a VR app for some sort of therapeutic purpose. Some therapies that we thought about included physical therapy, pain management, anxiety disorders, relaxation, and meditation. However, we identified some challenges and roadblocks to consider. For example, one of the biggest obstacles for creating a physical therapy VR app is the fact that movement and physical controls need to be more dynamic than the simple clicking controls that VR using Google cardboard can do. Upon brainstorming design ideas, we realized that many therapeutic techniques would be difficult to implement effectively in A-Frame in a relatively short time period. In addition to designing an aspirational use of VR, we wanted to create something that our classmates would find value in for them since they are the end users. Therefore, we turned our focus to stress-relieving and relaxation techniques such as meditation.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/0*ACnDsiAf0YKtK0kN" /><figcaption>Brainstorming ideas for Design VR for different types of therapies</figcaption></figure><p><strong><em>Chosen Idea: Designing VR for Guided Mindfulness Meditation</em></strong></p><p>Our chosen idea to design a meditative VR spawned from our previous idea to implement something therapeutic for the user. However, through ideation of potential therapeutic uses of VR, our team decided on meditation because it can provide health and wellness benefits to people in all walks of life, including often-stressed college students, our ultimate end users for our Design for Future Demo Day.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/290/0*hBu1TbZ7sdklT-D6" /><figcaption>Example of someone meditating in a VR setting</figcaption></figure><p>While researching<a href="https://www.medicalnewstoday.com/articles/320392.php"> types of meditation</a> and brainstorming potential aspects of meditation to incorporate, we were able to brainstorm many ideas that are relaxing and stress-relieving since meditation comes in many forms. Additionally, there are no set “right” and “wrong” ways to practice meditation, giving our team more creative freedom.</p><p>We ultimately decided to create a guided, <a href="https://www.verywellmind.com/mindfulness-meditation-88369">mindful meditation</a> for the following reasons:</p><ul><li>Certain forms of mindful meditation urge users to keep their eyes open and be present in their surroundings.</li><li>People can do it almost anywhere.</li><li>Mindful meditation is extensively studied and there are many <a href="https://www.bucknell.edu/about-bucknell/counseling-and-student-development-center/self-help-resources/mindfulness-exercises.html">examples</a> out there.</li></ul><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/0*LRwZDDbyCNra_zeq" /><figcaption>Elements of Mindfulness, an example being guided mindful meditation</figcaption></figure><h4><strong>Ideation: Defining the Mindful Meditation Experience and Mapping to VR</strong></h4><p>After deciding to design a guided, mindful meditation in VR and conducting preliminary research, our team sought to learn even more through actually experiencing it. We attended a Mindfulness Meditation event at Bucknell (here is an <a href="https://www.bucknell.edu/Documents/CounselingCenter/MindfulnessMenu.pdf">example</a>) as part of Mindfulness March and had many takeaways that helped us design our guided meditation in VR!</p><ul><li>There is no right and wrong way to meditate. Even a few minutes a few days a week is beneficial!</li><li>Importance of breathing and relaxing your body during the meditation</li><li>Mapping your surroundings and focus to your internal thoughts</li></ul><p>Next, we thought about how to apply a VR to a meditative environment, which poses some challenges and constraints due to the technology we are using. Some challenges and questions that we considered included are described below.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/760/0*yJ_L0DhN_bI57GKH" /><figcaption>Considerations for designing a meditative experience in a VR environment</figcaption></figure><p>We considered each of these components of the guided mindful meditation experience in VR during the prototyping stage.</p><h3><strong>Prototyping</strong></h3><p>After ultimately deciding to focus on designing a guided mindful meditation for our VR, we had to choose the components that we wanted to encompass in our VR through prototyping. Prototyping was conducted through sketching and utilizing the <a href="https://aframe.io/">A-Frame</a> technology to create and add 360 video environments. The two important elements of the experience to prototype were environment and the guided audio voice.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/0*vk9c62teXHp65Au7" /><figcaption>A-Frame</figcaption></figure><p><strong><em>Environments: </em></strong>For the environments, we immediately chose to prototype designs that incorporate <a href="https://www.mettle.com/360vr-master-series-free-360-downloads-page/">360 degree videos</a>. Meanwhile, we picked environments that we thought would be immersive for meditation. We also sketched ideas for the flow from environment to environment as the user progresses through the guided meditation.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/0*RIarWqEMp-altAFr" /><figcaption>Sketch of flow of environments throughout the meditation. Our team modified the order and the choice of scenes for the final VR product.</figcaption></figure><p><strong><em>Guided Voice Audio: </em></strong>After sketching and prototyping environments, we also identified and designed guided voiceovers to overlay each environment in order provide the full meditative experience. We wanted to choose scripts that encourage awareness of surroundings, promote relaxation, and help people reduce fixations on negative emotions. We consulted mindful meditation scripts such as those from <a href="https://mindfulnessexercises.com/guided-meditation-scripts/">mindfulness exercises</a> and wrote drafts of our own scripts.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/965/0*tYqGHf24U_Yo_jNz" /><figcaption>Part of the Meditation Script incorporated into the final VR Product</figcaption></figure><h3><strong>Formative Testing &amp; Feedback</strong></h3><p>While prototyping designs for our guided mindful meditation in A-Frame and through sketching, we iteratively tested and asked users for feedback in order to make design decisions for our final product. Users provided valuable insights on what environments they truly felt were the best to meditate and relax in. While we didn’t have our recordings of our written meditations complete, we conducted Wizard of Oz testing with our chosen environments and other meditation recordings. In “Wizard of Oz” testing, developers define a set of actions for game input for the participant and act as the controller while the participant uses those actions to interact with the game.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/0*S1Le_qBaIT2NLjgC" /><figcaption>User testing with Google cardboard</figcaption></figure><p>In addition to getting user feedback on the environment, guided audio, music and sounds, we also did formative testing with the equipment (VR Head Piece) to ensure that it was comfortable enough and provided a relaxing environment for users. In order to enhance the meditative experience, we also wanted the VR head piece to be hands-free with good-quality sound so that users can focus without distractions. After asking users to try a variety of options, we decided to use <a href="https://www.amazon.com/VR-BOX-2-Virtual-Reality-Goggle/dp/B01HUW65LI">VR Box goggles</a> with Beats headphones. Users felt that this combination for vision and sound provided the most immersive experience.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/838/1*Qh3Exqb97VvwyCYq1tJUcA.png" /><figcaption>User testing with theVR Box</figcaption></figure><h3><strong>Building the VR</strong></h3><p>For incorporated guided meditation audio, we recorded three separate narratives to fit each scene using <a href="https://www.audacityteam.org/">Audacity</a>. Inspired by <a href="https://www.eg.bucknell.edu/~emp017/">Professor Peck</a>, we decided to switch between different environments as the users close their eyes and look down. We needed to ensure that we have fine control over stopping and switching between videos and sounds.</p><p>The hardest part of implementation was getting the VR built in A-Frame working on mobile and browser.Since we decided to switch between different environments, we needed to ensure that we have fine control over stopping and switching between videos and sounds. The hardest part of implementation was getting the VR built in A-Frame working on mobile and browser. It took us three iterations to get to the demo day version.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/0*Qi4LEkxj5uF1WmAi" /><figcaption>Guided Mindful Meditation Iterations</figcaption></figure><p>The first iteration switches between meditation scenes by changing web pages. Although this method gives us more control over what is playing what is not, there is a significant gap (about three seconds) between the transition. Even though we asked people to close their eyes while switching scenes, we felt that the three seconds lag could worsen the user experience. Therefore, we decided to make the transition by hiding and displaying the elements.</p><p>From iteration 2 to iteration 3, we separated the video and audio and made some enhancements using Final Cut and Audition so that the videos could be playing at the background since sounds were easier to load and control.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/960/0*ClE1ch402mLNwjaw" /><figcaption>Iteration 1: We could see the white blank transitions between scenes</figcaption></figure><figure><img alt="" src="https://cdn-images-1.medium.com/max/600/0*QJfVE04eWFwHDBAL" /><figcaption>At iteration 3, the transition is seamless</figcaption></figure><p>After making sure the the videos, audios and transitions move smoothly in a PC browser, we went on testing on our iphones. We noticed a limitation of the browser in iOS in which sounds do not play automatically and requires a click input by the user.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/739/0*686pY6wPLoy0vDWx" /><figcaption>The IOS Browser limitation</figcaption></figure><p>Therefore, we used an Android phone for testing and deploying.</p><h3><strong>Demo Day &amp; More User Feedback</strong></h3><p>After going through many iterations of the design, testing, and building, we presented our Guided Mindful Meditation VR on Demo Day and received more feedback from users. Overall, the feedback we received was positive. One of the major highlights was the overlaid, personally recorded meditation. Users felt that the sound quality was great and the voice was soothing. Users also appreciated the ability to choose which portal you can enter and the seamless exit from each scene.</p><p>While users were intrigued by meditative experience, they also had some features that they wish we had added. Many wanted higher resolution environments. Users also hoped for more choices for environments to meditate in and the ability to turn off the voiceover if they desire. Our team received insightful feedback on Demo Day in order to make improvements for future iterations.</p><h3><strong>Conclusion &amp; Reflection: Creating an Aspirational Use of VR</strong></h3><p>Through designing a VR for guided mindful meditation and keeping our design goal in mind throughout our design process, our team collectively created a VR experience that we see as aspirational. Our product went through multiple iterations and utilizes VR technology to benefit peoples’ mental health and well-being. It provides an escape from stressors of everyday life in the form of a meditative experience. Our hope for the future is that rapidly-advancing technologies such as VR can be used in ways that promote health and happiness.</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=48ed488993df" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[“Dance With Your Hands” With Tap Tap Revolution!]]></title>
            <link>https://klordihavemercy.medium.com/dance-with-your-hands-with-tap-tap-revolution-31c0f02f35d7?source=rss-1f00722da339------2</link>
            <guid isPermaLink="false">https://medium.com/p/31c0f02f35d7</guid>
            <category><![CDATA[fun]]></category>
            <category><![CDATA[expression]]></category>
            <category><![CDATA[hcd]]></category>
            <category><![CDATA[virtual-reality]]></category>
            <category><![CDATA[hci]]></category>
            <dc:creator><![CDATA[Katherine Lordi]]></dc:creator>
            <pubDate>Sun, 31 Mar 2019 20:57:02 GMT</pubDate>
            <atom:updated>2019-03-31T21:10:57.620Z</atom:updated>
            <content:encoded><![CDATA[<p>Meet our team! <a href="https://medium.com/u/e7d78cabd961">Dan Kershner</a>, <a href="https://medium.com/u/1f00722da339">Katherine Lordi</a>, <a href="https://medium.com/u/b6e4fd78cdfb">Samantha Nolle</a>, and <a href="https://medium.com/u/e805c20bad0e">Jordan Sechler</a></p><h3><strong>Introducing… Tap Tap Revolution! A Spin-off of Dance Dance Revolution</strong></h3><p>Thinking back to fun childhood memories spent at the arcade playing games and winning tickets in exchange for prizes, Dance Dance Revolution (DDR) was always one of the largest games in the entire arcade that required the most physical activity.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/250/0*PQ-9gT9hKRaAiEk3" /><figcaption>Dance Dance Revolution (DDR) Arcade Game</figcaption></figure><p>DDR is fun to watch (and play!) because it requires rhythm, coordination, dancing ability, and willingness to potentially look silly in front of strangers. Keeping bodily expression and fun as the primary design goal for this <a href="https://bucknell-hci-2019.github.io/designs/gesture_assn.html">design sprint</a>, our team decided to recreate an online version of the beloved DDR game called<a href="http://www.flashflashrevolution.com/FFR_the_Game.php"> “Flash Flash Revolution”</a> that uses the basic arrow keys. In order to make the game expressive using a <a href="https://www.interaction-design.org/literature/book/the-encyclopedia-of-human-computer-interaction-2nd-ed/3d-user-interfaces">3D UI</a>, we enabled users to “dance with their hands” through the use of Python code and visual detection of the user interface using a webcam. In turn, “Tap Tap Revolution”, our rendition of the game, was born.</p><iframe src="https://cdn.embedly.com/widgets/media.html?src=https%3A%2F%2Fwww.youtube.com%2Fembed%2Fbr0iUxajNDI%3Ffeature%3Doembed&amp;url=http%3A%2F%2Fwww.youtube.com%2Fwatch%3Fv%3Dbr0iUxajNDI&amp;image=https%3A%2F%2Fi.ytimg.com%2Fvi%2Fbr0iUxajNDI%2Fhqdefault.jpg&amp;key=a19fcc184b9711e1b4764040d3dc5c07&amp;type=text%2Fhtml&amp;schema=youtube" width="854" height="480" frameborder="0" scrolling="no"><a href="https://medium.com/media/c98297ce84400115587af43efbe29611/href">https://medium.com/media/c98297ce84400115587af43efbe29611/href</a></iframe><h3><strong>Our Design Process</strong></h3><h3><strong>Choosing the Game… Trial and Fun!</strong></h3><p>Before settling on Tap Tap Revolution for our game, we brainstormed a handful of fun and popular web games that we liked from our childhoods, and brainstormed ideas for the 3D UI by trying gestures ourselves through “Wizard of Oz” style testing. In Wizard of Oz testing, developers define a set of actions for game input for the participant, and the participant uses those actions to interact with the game. However, meanwhile, one developer acts as the controller.</p><p>While brainstorming, we were careful to focus on games that were doable in the context of the tools we had available to us, namely the <a href="https://www.leapmotion.com/">Leap Motion Controllers </a>and laptop webcams. We wanted to choose a game that not only worked easily with these forms of technology, but that would also be intuitive and easy to learn for first time users.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/0*YAZISuiDYJExj9Xw" /><figcaption>Playing around with laptop webcam for image detection</figcaption></figure><p>Most importantly, we wanted a game that was fun and engaging (emphasizing fun and expression). We imagined that “engaging” could come in many forms, such as nostalgia, movement, colorful or exciting visuals, a fast pace, and/or use of music or auditory elements. Inspired by <a href="https://drive.google.com/file/d/0B9wW7gtF6dvRd0lrQUlpQVBHczg/view">“Making Things Engaging”</a>, we sought important elements of engaging products including beauty of interaction, enjoyment of the experience, rich actions, and doing rather than thinking. From there, we sought to settle on a game that incorporated these aspects of an engaging experience, doability using the tools available to us, and intuitiveness for users.</p><h4>Idea #1 Slither.io</h4><p>The first web game we considered was <a href="http://www.agame.com/game/slitherio">Slither.io</a>, a game in which a user controls the continuous motion of a colorful snake to “eat” orbs and not get absorbed by other snakes. We felt that this game would integrate easily with the capabilities of the Leap Motion in the sense that the snake may be moved to the left or right or with a boost of speed. We envisioned a user moving their flattened palm to the left or the right to control direction, and pinching or unpinching their fingers to control speed. We imagined that these motions would need to be explained to a user, but since there were only three variations to remember, the learning process would be simple. Additionally, we felt that the element of nostalgia for past users, as well as colorful visuals and movements (including variation of speed), would all contribute to an engaging experience for users.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/750/0*kyYJ4HnMzgk9Ej4-" /><figcaption>Wizard of Oz testing for Slither.io game. User clenches her fist to indicate a boost in speed.</figcaption></figure><p>After “Wizard of Oz”-ing the Slither.io idea for Leap Motion, we decided to think about games involving more interactive hand gestures to control characters.</p><h4>Idea #2 Frogger</h4><p>The second web game we brainstormed was <a href="http://www.frogger.net/">Frogger</a>, a game in which the user controls the forward motion of a frog across a game board with moving tiles and obstacles. We felt that the objective of this game could be integrated with the capabilities of the leap motion through the clenching and unclenching of a fist to control forward motion of the frog. We imagined that like Slither.io, these motions would also need to be explained to a user, but as they were few in number, they would not be overwhelming for a user to remember. Furthermore, we felt that Frogger also contributed to a feeling of nostalgia for users, as well as the excitement of both moving game pieces and the movement of the frog.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/0*jA6LviwzyxJghxkb" /><figcaption>Wizard of Oz testing for Frogger. User clenches her fist to move frog across the busy road and tilts hand left and right to move frog left or right</figcaption></figure><p>After “Wizard of Oz”-ing the idea for Frogger using Leap Motion, one reoccurring issue encountered was the quickness required to move the frog. Therefore, test users were a little overwhelmed with the speed of the game. However, we noticed that users quickly picked up the mapping of frog motions to hand motions with little instruction.</p><h4>Chosen Idea: Flash Flash Revolution</h4><p>Our team thought of DDR (Dance Dance Revolution) because we found a version of it online called <a href="http://www.flashflashrevolution.com/">Flash Flash Revolution</a> (FFR). We liked this game for a number of reasons. In addition to being familiar and nostalgia provoking like Frogger, the element of music and musical coordination made FFR fun and engaging to play. By trying the hand gestures ourselves through Wizard of Oz testing and creating life size arrow keys on paper that corresponded to the arrow keys on the keyboard, we found that not only did we have to move our hands to match the screen, but also to match the rhythm of the music. This game combined the engagement of hand gestures with the excitement of music through coordination of hands and song. Additionally, unlike the other games we considered, two hands are needed to play rather than just one!</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/0*Ov6YfxRPH7JPDFZw" /><figcaption>On-screen user interface of flash flash revolution. When translating the arrow keys to hand gestures, two hands are required to play the game.</figcaption></figure><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/0*yn0NctkKrcSfB15y" /><figcaption>Flash Flash Revolution provides a wide range of difficulty settings and song choices ranging from easiest to brutal.</figcaption></figure><p><a href="http://faculty.washington.edu/ajko/books/uist/hands.html">Andrew Ko’s chapter on hands</a> and discussion about Hand Tracking had great points that set the FFR idea apart from the others. Hand tracking systems work well with tasks in 3D that require pointing and spatial manipulation (such as dancing and hitting arrow keys) because “they treat the hand as a continuous input device and estimate the hand’s real-time position and orientation.” In our hand tracking system, the webcam and color recognition techniques would help track when a key is pressed in the FFR game. Even though hand tracking systems introduce<a href="https://faculty.washington.edu/ajko/books/design-methods/how-to-design-user-interfaces.html"> gulfs of evaluation and gulfs of execution</a>, according to Ko, the severity of these gulf may be lower. In addition to the fun of the FFR game, this was another motivation in choosing it for our final product.</p><h3><strong>Formative Testing: “Wizard-Of-Oz”ing Tap Tap Revolution</strong></h3><p>By means of “Wizard of Oz” testing of our Tap Tap Revolution idea with other students, we were able to see if the tapping motions that we planned for the game were indeed fun, expressive, and intuitive for users for the design of the 3D UI.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/0*a8-n8e1eoSTpzq1H" /><figcaption>User interface for our Wizard of Oz testing of FFR. Users pressed the arrows and went through the motions of the game while developers pressed the actual arrows on the laptop.</figcaption></figure><p>Following the completion of some wizard of oz testing for Tap Tap Revolution, we saw enjoyment and ease of use by users in the following ways:</p><ul><li>Users enjoyed having a precise location to “tap” physically.</li><li>Users became more and more comfortable the more they “played.”</li><li>Users found the mapping of hands keys to arrow keys and music intuitive and amusing, especially when many have tried DDR or another alike version of the game before.</li></ul><h3><strong>Building Tap Tap Revolution: Python and Vision Detection via Webcam</strong></h3><p>We began coding a prototype in <a href="https://p5js.org/">p5.js</a> to see if game implementation was even possible. It worked by using the webcam to identify four specific pixels on the screen and examine the color of each. When the color of one of these pixels changed, which would happen when a user covered it with their hand, it would register that change and then create input to Flash Flash Revolution (FFR). However, we quickly discovered that p5.js had no easy way to create input for a browser game. This caused us to switch to python, which was actually very easy due to a few libraries we imported. It worked much the same as the original prototype, and could now send key presses to the game. This allowed us to map each of the four pixels to an arrow key, so that when the user covered a pixel, the proper arrow key that it represented would be pressed and given as input to FFR.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/0*g7HX4W9NQy_In14n" /><figcaption>Testing to see if altering color of pixels by covering paper with hand registers change to use as input to FFR.</figcaption></figure><p>This seemed to work, but we were getting lots of false positives because the color of a single pixel was very unreliable. To fix this, we took the average color of a circle with a radius of 64 pixels, rather than the color of a single pixel. This gave us much more reliable results and virtually no false positives. To improve user experience, we placed white sticky notes at the location of each of these circles, so all they had to do was cover one of these sticky notes with their hand to simulate pressing an arrow key.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/0*6HyVjRj-oWG5hZnn" /><figcaption>To get rid of false positives in color/pixel recognition, we took the average color of a circle with radius of 64 pixels (pictured on laptop).</figcaption></figure><h3><strong>User Testing Post-Development</strong></h3><p>Once we had a working game, we had several people test it and give us feedback. Some people who tested the game for us had trouble with the controls because they would let their hands hover over the sticky notes, which caused false positives. However, once we explained how it worked with the webcam they made sure to keep their hands back until they wanted to trigger an input. Once they figured out how it works and got the hang of it, most users really enjoyed the game. They told us it was fun to play a game familiar to them from their childhood with totally new controls.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/0*ZmwN5S4cd_amfcha" /><figcaption>Users enjoying and providing user feedback on Tap Tap Revolution!</figcaption></figure><p>Some users told us that while it was fun and a cool new way to play the game, it was not a perfect input method because it was more difficult than the traditional way of just using the arrow keys on the keyboard. For many of the harder songs available to play, it was near impossible to keep up with our new control method. However, since the point of this project was to create a fun new input method to the game, rather than one that made it easier to play, we decided to stick with our implementation because the users were having fun on the easier songs. It may not be the ideal input method for playing this game well, but it definitely seems to be a fun one.</p><h3><strong>Demo Day &amp; User Feedback</strong></h3><p>The demo day went very well, and most people who tried our game thoroughly enjoyed it and had fun with it! The feedback that we received showed us that most people loved the game and controls we implemented. They said it was fun to play, very intuitive to control, matched their motions well, and was simple overall. The 3D user input also better connected to the real version of the Dance Dance Revolution game that evokes nostalgia among users.</p><p>People also gave many suggestions for improvement, revolving around the controls and the game. Most people wanted the controls to be more precise and reliable. It wasn’t too easy to quickly cover the right spot on the sticky notes to activate an input, which caused the game to be more difficult than it would be with normal controls. Some people also wanted more controls and interactivity, such as a pause button or the ability to choose other songs. Currently the only way to do these things is to use the actual computer with the real controls, not our 3D input. Implementing a few more controls and tuning the current inputs to be more precise could definitely improve our game for future iterations.</p><h3>Conclusion: Designing for Fun/Expression</h3><p>Through designing for fun and expression in this <a href="https://bucknell-hci-2019.github.io/designs/gesture_assn.html">design sprint</a>, our team implemented a 3D UI and designed an interface that prioritizes bodily expression and fun. “Tap Tap Revolution” creates a fun, new way to play the beloved game Dance Dance Revolution that allows people to “dance with their hands” and follow the rhythm of the music and hit the arrows to earn points. The intuitive and expressive hand motions along with a variety of song options and difficulty levels also brings out players’ competitive spirit. Our team’s goal was to create a game that provides a fun user experience. Through brainstorming, wizard of oz testing, and user testing after implementation, we met our goal and identified ideas for future iterations of “Tap Tap Revolution.”</p><p>Find the source code <a href="https://gitlab.bucknell.edu/jls102/handhandrevolution">here</a>!</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=31c0f02f35d7" width="1" height="1" alt="">]]></content:encoded>
        </item>
    </channel>
</rss>