<?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 Eniola Olaleye on Medium]]></title>
        <description><![CDATA[Stories by Eniola Olaleye on Medium]]></description>
        <link>https://medium.com/@eniolaolaleye426?source=rss-af87cc38759c------2</link>
        <image>
            <url>https://cdn-images-1.medium.com/fit/c/150/150/1*WKEEJTfvEphRYKXkypM9sg.jpeg</url>
            <title>Stories by Eniola Olaleye on Medium</title>
            <link>https://medium.com/@eniolaolaleye426?source=rss-af87cc38759c------2</link>
        </image>
        <generator>Medium</generator>
        <lastBuildDate>Thu, 19 Nov 2026 17:27:49 GMT</lastBuildDate>
        <atom:link href="https://medium.com/@eniolaolaleye426/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[WINNING APPROACH ML COMPETITION 2022]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://medium.com/machine-learning-insights/winning-approach-ml-competition-2022-b89ec512b1bb?source=rss-af87cc38759c------2"><img src="https://cdn-images-1.medium.com/max/854/1*kMhhoSQxx_bYdcSw93iSAw.png" width="854"></a></p><p class="medium-feed-snippet">Hoping to win a machine learning competition in 2022? Here&#x2019;s what you need to know. I collaborated with ML Contests, using their database&#x2026;</p><p class="medium-feed-link"><a href="https://medium.com/machine-learning-insights/winning-approach-ml-competition-2022-b89ec512b1bb?source=rss-af87cc38759c------2">Continue reading on Machine Learning Insights »</a></p></div>]]></description>
            <link>https://medium.com/machine-learning-insights/winning-approach-ml-competition-2022-b89ec512b1bb?source=rss-af87cc38759c------2</link>
            <guid isPermaLink="false">https://medium.com/p/b89ec512b1bb</guid>
            <category><![CDATA[machine-learning]]></category>
            <category><![CDATA[artificial-intelligence]]></category>
            <category><![CDATA[kaggle]]></category>
            <category><![CDATA[data-science]]></category>
            <category><![CDATA[competitive-programming]]></category>
            <dc:creator><![CDATA[Eniola Olaleye]]></dc:creator>
            <pubDate>Sun, 13 Mar 2022 17:48:40 GMT</pubDate>
            <atom:updated>2022-03-13T17:48:40.164Z</atom:updated>
        </item>
        <item>
            <title><![CDATA[How To Win Any ML Contest]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://medium.com/machine-learning-insights/how-to-win-any-ml-contest-244a12c62f30?source=rss-af87cc38759c------2"><img src="https://cdn-images-1.medium.com/max/714/0*ukQ7dnRW8Y_07Wk_" width="714"></a></p><p class="medium-feed-snippet">Hoping to win a machine learning competition in 2021? Here&#x2019;s what you need to know. I collaborated with ML Contests, using their database&#x2026;</p><p class="medium-feed-link"><a href="https://medium.com/machine-learning-insights/how-to-win-any-ml-contest-244a12c62f30?source=rss-af87cc38759c------2">Continue reading on Machine Learning Insights »</a></p></div>]]></description>
            <link>https://medium.com/machine-learning-insights/how-to-win-any-ml-contest-244a12c62f30?source=rss-af87cc38759c------2</link>
            <guid isPermaLink="false">https://medium.com/p/244a12c62f30</guid>
            <category><![CDATA[competition]]></category>
            <category><![CDATA[kaggle]]></category>
            <category><![CDATA[machine-learning]]></category>
            <category><![CDATA[data-science]]></category>
            <category><![CDATA[ai]]></category>
            <dc:creator><![CDATA[Eniola Olaleye]]></dc:creator>
            <pubDate>Tue, 13 Apr 2021 18:59:26 GMT</pubDate>
            <atom:updated>2021-04-13T18:59:26.142Z</atom:updated>
        </item>
        <item>
            <title><![CDATA[Customize your github profile with a markdown file]]></title>
            <link>https://eniolaolaleye426.medium.com/customize-your-github-profile-with-a-markdown-file-7ac49faec98a?source=rss-af87cc38759c------2</link>
            <guid isPermaLink="false">https://medium.com/p/7ac49faec98a</guid>
            <category><![CDATA[md]]></category>
            <category><![CDATA[github]]></category>
            <category><![CDATA[software-development]]></category>
            <category><![CDATA[markdown]]></category>
            <category><![CDATA[coding]]></category>
            <dc:creator><![CDATA[Eniola Olaleye]]></dc:creator>
            <pubDate>Fri, 11 Dec 2020 02:37:11 GMT</pubDate>
            <atom:updated>2020-12-11T12:38:55.697Z</atom:updated>
            <content:encoded><![CDATA[<p>Github recently introduced a new feature for Developers which allow you pin a markdown file (called special repository) to your GitHub profile, to let you describe more about your skill sets , what project you are working on and display a general overview of your portfolio.</p><p>Some of the interesting ones i have seen:</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*zubU5CcPaAtWau1ZJnWuJQ.png" /><figcaption><a href="https://medium.com/u/10cf0dba197a">Rising Odegua</a></figcaption></figure><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*3Frjns31QJuRNk9jua7bLg.png" /><figcaption><a href="https://medium.com/u/22af4904d21e">Bamigbade Opeyemi</a></figcaption></figure><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*ufN53Mbad6nH7x9FuGTNNw.png" /><figcaption><a href="https://medium.com/u/af87cc38759c">Eniola Olaleye</a></figcaption></figure><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*yD97dYGlcCiFbuj8SDaM8g.png" /><figcaption>Galileo himself!</figcaption></figure><p><strong>Markdown</strong> is a lightweight markup language with plain-text-formatting syntax, it is used for formatting readme <strong>files</strong>, for writing messages in online discussion forums, and to create rich text using text editor.</p><h3><strong><em>MARKDOWN SYNTAX</em></strong></h3><p>markdown has a very simple syntax the major one we would use is how to add an image , create headers , list and links.</p><h3>Headers :</h3><p>#an &lt;h1&gt; tag , ## an&lt;h2&gt; tag , #### an &lt;h4&gt; tag</p><h3>Emphasis:</h3><p>*This text will be italic*<br>_This will also be italic_<br>**This text will be bold**<br>__This will also be bold__<br>_You **can** combine them_</p><h3>LISTS:</h3><pre>* Item 1<br>* Item 2<br>  * Item 2a<br>  * Item 2b</pre><h3>IMAGES:</h3><pre>![GitHub Logo](/images/logo.png)<br>Format: ![Alt Text](url)</pre><h3>Links</h3><pre>http://github.com - automatic!<br>[GitHub](http://github.com)</pre><h3>MAIN DEAL</h3><p>we would now see how we can pin a readme file to create a beautiful github profile.</p><h3>PREREQUISITES:</h3><ol><li>A GitHub account</li><li>Basic mark down Knowledge (which we have covered above)</li><li>Willingness to learn</li></ol><h3>STEPS</h3><ol><li>create a new <strong>special repository </strong>with your GitHub username my username is <strong>galileoSolution</strong> so i created a new repository called <strong>galileoSolution.</strong></li></ol><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*bChL9l31G56Jstb09yvxsA.png" /></figure><p>2. Ensure the repository is set public and click on the checkbox: <em>add a readme file then click on </em>create repository.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*ZXiQi72f23dQTluqngNFRg.png" /><figcaption>After this you are set for greatness!</figcaption></figure><p>After creating the repository since you added a readme file GitHub helps you with a free template which you can edit to suite your personality!</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*riiu9CvsVA31t7mk9ed1UA.png" /><figcaption>sample template</figcaption></figure><p>Now we are all set you can edit this add texts, images ,tables and list.</p><p>This is my own finished copy!</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*OZv1QQ59WC9Zaoe96RTXMw.png" /><figcaption>Galileo</figcaption></figure><p>If this has helped you give it a clap and i would also like to see your profile if you are done send a link to your GitHub profile or a screen shot thank you!</p><p>mine is <a href="https://github.com/galileoSolution">here</a> — my GitHub</p><p>connect with me on <a href="https://twitter.com/galileoeni">twitter</a> and <a href="https://www.linkedin.com/in/eniola-olaleye-361b39160/">linkedin</a>.</p><p><strong><em>muchas gracias.</em></strong></p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=7ac49faec98a" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[How I cracked a Data Science Hackathon]]></title>
            <link>https://medium.com/analytics-vidhya/5th-place-solution-mobile-money-and-financial-inclusion-in-tanzania-challenge-16e43e4d18f8?source=rss-af87cc38759c------2</link>
            <guid isPermaLink="false">https://medium.com/p/16e43e4d18f8</guid>
            <category><![CDATA[machine-learning]]></category>
            <dc:creator><![CDATA[Eniola Olaleye]]></dc:creator>
            <pubDate>Thu, 04 Jul 2019 17:45:04 GMT</pubDate>
            <atom:updated>2019-07-10T06:29:06.451Z</atom:updated>
            <content:encoded><![CDATA[<p>You know how competitions can be quite frustrating and strenuous especially when its a week before the deadline. You begin to refresh the page every time, looking at your rank. Over time, I have gotten used to it, and the most interesting part is you get to learn a lot of things aside chasing the prize I gained a lot of knowledge.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/214/1*p7bypxzBq1pHQ337ktYfnw.jpeg" /><figcaption>This guy said it all.</figcaption></figure><p>Recently, I took part in the zindi competition:</p><p><a href="https://zindi.africa/competitions/mobile-money-and-financial-inclusion-in-tanzania-challenge/leaderboard">Mobile Money and Financial Inclusion in Tanzania Challenge</a></p><p>I was 5th and was placed at #5 (out of 164 teams) on the leaderboard.</p><p>In this blog post, I will summarise the main ideas of my solution.</p><h3>Problem Description</h3><p>The objective of this competition is to create a machine learning model to predict which individuals are most likely to use mobile money and other financial services (savings, credit, and insurance).</p><p>This model can help mobile money providers target new clients and markets across Tanzania more effectively, and also help financial services providers cross-sell other financial services (savings, credit, and insurance) to the existing mobile money customer base.</p><p><strong>There are 4 approaches for improving your model:</strong></p><ol><li>Improve Performance With Data.</li><li>Improve Performance With Algorithms.</li><li>Improve Performance With Tuning.</li><li>Improve Performance With Ensembles.</li></ol><p><strong>I decided to follow the 1st approach, which is adding more data.</strong></p><p>The gains often get smaller the further you go down the list. For example, a new framing of your problem or more data is often going to give you more payoﬀ than tuning the parameters of your best performing algorithm. Not always, but usually.</p><p>Tactics:<br> <strong>Get More Data: </strong>Modern nonlinear machine learning techniques like deep learning continue to improve in performance with more data.<br> <strong>Invent More Data: </strong>If you can’t get more data, can you generate new data? Perhaps you can augment or permute existing data or use a probabilistic model to generate new data.<br> <strong>Clean Your Data:</strong> Can you improve the signal in your data? Perhaps there are missing or corrupt observations that can be ﬁxed or removed, or outlier values outside of reasonable ranges that can be ﬁxed or removed in order to lift the quality of your data.<br> <strong>Transform Your Data: </strong>Can you reshape your data distribution? Making input data more Gaussian or passing it through an exponential function may better expose features in the data to a learning algorithm.</p><p><strong>Solution 1:</strong></p><p>Looking at the data, we have latitude and longitude features so I reverse-geoencoded it with geopy to get the region district and street of each particular ID.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*bb0nzW2htgekNoJA5JsxwQ.jpeg" /><figcaption>The data.head() view.</figcaption></figure><p>After reverse geoencoding, I had this:-</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*3KeHtw8UltRIDIKp15Ez5A.jpeg" /><figcaption>reverse encoding</figcaption></figure><p>I was able to get 4 features from reverse encoding which are zone, district, region and street.</p><p><strong>Solution 2:</strong></p><p>There was a folder provided by zindi called fsdt folder, so I did some engineering to get new longitudes and latitudes. Based on these values, I calculated the Haversine distance.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*rqJc4eeySuux7Um5SZbbfw.jpeg" /><figcaption>Haversine distance</figcaption></figure><p>Since the entire code is too long, I will share a link to it on my github.</p><p><strong>Solution 3:</strong></p><p>Another technique that worked was using arcgis to enrich my dataset with some other datasets.</p><p>I created a video on how to do implement the above:</p><iframe src="https://cdn.embedly.com/widgets/media.html?src=https%3A%2F%2Fwww.youtube.com%2Fembed%2F8i6hQn5yY1s%3Fstart%3D16%26feature%3Doembed%26start%3D16&amp;url=http%3A%2F%2Fwww.youtube.com%2Fwatch%3Fv%3D8i6hQn5yY1s&amp;image=https%3A%2F%2Fi.ytimg.com%2Fvi%2F8i6hQn5yY1s%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/906335358875e82d6a5f57eabc50bbae/href">https://medium.com/media/906335358875e82d6a5f57eabc50bbae/href</a></iframe><p>As I said earlier, a competition is not all about the money, you also get to learn a lot.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*HfMoEMr-eGzc1e5iWZUJOw.jpeg" /><figcaption>My solution getting placed first</figcaption></figure><h3><strong>Final Word Before You Go</strong></h3><p>How To Get Started: You do not need do everything. You just need one good idea to get a lift in the performance of your model.</p><p>Here’s how to handle the problem statement:<br>1. Pick one group to work on: a) Data b) Algorithms c) Tuning d) Ensembles<br>2. Pick one method to work on the group.<br>3. Pick one algorithm to try from the chosen method.<br>4. Compare the results, retain the solution if there was an improvement.<br>5. Repeat.</p><p>My codes <a href="https://github.com/galileoSolution/5th-place-solution-Mobile-Money-and-Financial-Inclusion-in-Tanzania-Challenge">https://github.com/galileoSolution/5th-place-solution-Mobile-Money-and-Financial-Inclusion-in-Tanzania-Challenge</a></p><p>“We’re entering a new world in which data may be more important than software.” — <a href="https://www.oreilly.com/tim/"><em>Tim O’Reilly</em></a><em>, founder, </em><a href="https://www.oreilly.com/"><em>O’Reilly Media</em></a><em>.</em></p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=16e43e4d18f8" width="1" height="1" alt=""><hr><p><a href="https://medium.com/analytics-vidhya/5th-place-solution-mobile-money-and-financial-inclusion-in-tanzania-challenge-16e43e4d18f8">How I cracked a Data Science Hackathon</a> was originally published in <a href="https://medium.com/analytics-vidhya">Analytics Vidhya</a> on Medium, where people are continuing the conversation by highlighting and responding to this story.</p>]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[ANALYTICAL HIERACHY PROCESS FOR SELECTING THE BEST PRESIDENTIAL CANDIDATE]]></title>
            <link>https://medium.com/the-data-league/analytical-hierachy-process-for-selecting-the-best-presidential-candidate-dc77bf1d4f1c?source=rss-af87cc38759c------2</link>
            <guid isPermaLink="false">https://medium.com/p/dc77bf1d4f1c</guid>
            <category><![CDATA[ahp]]></category>
            <category><![CDATA[artificial-intelligence]]></category>
            <category><![CDATA[python]]></category>
            <category><![CDATA[leadership]]></category>
            <dc:creator><![CDATA[Eniola Olaleye]]></dc:creator>
            <pubDate>Sun, 17 Mar 2019 16:14:38 GMT</pubDate>
            <atom:updated>2019-03-17T21:45:39.478Z</atom:updated>
            <content:encoded><![CDATA[<p><strong>ANALYTICAL HIERARCHY PROCESS FOR SELECTING THE BEST PRESIDENTIAL CANDIDATE</strong></p><p><strong>ASSIGNMENTS</strong></p><p><strong>COURSE : MATHEMATICAL MODELING FOR ARTIFICIAL INTELLIGENT SYSTEMS</strong></p><p><strong>UNIVERSITY OF LAGOS (DEPARTMENT OF SYSTEMS ENGINEERING)</strong></p><p>YOU CAN GET THE LINK TO MY CODES HERE</p><p><a href="https://github.com/galileoSolution/AHP-ASSIGNMENTS-UNILAG/blob/master/AHP%20ASSIGNMENT.ipynb">galileoSolution/AHP-ASSIGNMENTS-UNILAG</a></p><p>First of all what is AHP?</p><p>Analytic Hierarchy Process (AHP) is one of Multi Criteria decision making method that was originally developed by Prof. Thomas L. Saaty. In short, it is a method to derive ratio scales from paired comparisons. The input can be obtained from actual measurement such as price, weight etc., or from subjective opinion such as satisfaction feelings and preference. AHP allow some small inconsistency in judgment because human is not always consistent. The ratio scales are derived from the principal Eigen vectors and the consistency index is derived from the principal Eigen value.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/400/1*oxVtkpG8gi12rp0yv_IELA.jpeg" /><figcaption>THAT DEFINITION IS TURNIONIWON.</figcaption></figure><p>The <strong>Analytic Hierarchy Process (AHP)</strong> is a structured technique for organizing and analyzing complex decisions.</p><ul><li>It is a practical approach to solving complex decision problems involving the comparisons of attributes or alternatives.</li></ul><h3>Reasons to Use Analytic Hierarchy Process for Collaborative Decision Making</h3><h3>1. Well-proven</h3><p>For the last 30–35 years AHP has been thoroughly tested by thousands of organizations from around the globe… and it seems to work!</p><p><strong>There are lots of case studies that describe how large organizations used AHP for their strategic decisions to achieve better outcomes.</strong></p><h3>2. Broad set of applications</h3><p>When you look into the case studies you will notice that it was used for variety of decision making problems.</p><p><strong>There are AHP applications related to </strong><a href="https://www.transparentchoice.com/project-prioritization"><strong>project prioritization</strong></a><strong>, vendor selection, technology selection, site selection, hiring decision and more…</strong></p><p>Having one good approach lets good decision making become part of your everyday processes; part of your culture.</p><h3>3. Intuitive and easy to use</h3><p><strong>People don’t feel comfortable taking recommendations from software if they don’t understand how it works.</strong> They don’t need to know the details but they want to understand the idea behind it.</p><p>For AHP, you break a complex decision into explicit goals, alternatives and criteria. You prioritize criteria and evaluate alternatives in light of those criteria. People get it.</p><p>In contrast, some more recently developed methodologies have a process and underlying math that is so complex that the software becomes a <em>“mathematical black box”</em>. It takes your input and returns recommendations. What happens in between is a mystery (at least for a regular human being) and that undermines trust. And <a href="https://blog.transparentchoice.com/importance-of-confidence-to-project-outcomes">trust is really important</a> when it comes to the final outcome.</p><p><strong>Using Analytic Hierarchy Process for your collaborative decision making works because, with AHP, you can explain how it works.</strong></p><h3>4. Designed for multi-criteria</h3><p><strong>When you make important decisions, there are always conflicts between criteria.</strong> For example, “minimizing price” and “maximizing quality” are often contradictory goals. This is made worse when you’re working in a team. Collaborative decision making, by definition, means people have different views and priorities.</p><p>Decision making best practice involves taking into account all important criteria. However, this “best practice” is often ignored as <em>multi-criteria analysis is much more challenging than, say, making a decision based on just the price</em>.</p><p><strong>Analytic Hierarchy Process allows you to take into account all important criteria and to organize them into a hierarchy.</strong></p><h3>5. Builds alignment around criteria priorities</h3><p>Some decision-making methodologies ask participants to assign weights to criteria. The question is, <em>“How should I set those weights?”</em> Well, however Fred in Finance does it, Sally in Sales will disagree.</p><p><strong>Participants always have different priorities and without a supporting process, it is hard to reach consensus. Some methodologies are missing this key mechanism. It leaves your group with an unresolved problem.</strong></p><p>And then the very smart quants dive in. They’ve developed another group of methods where weight of criterion is not a value but function. From theoretical point of view this might be a good concept but it is usually very hard to use for real collaboration.</p><p>If it is hard to agree on a value, and people need sensitivity analysis to check different scenarios, it will be much harder to agree on a function with a weird shape. How was the function developed? Shouldn’t it be a bit different? Remember what I wrote about <em>“mathematical black boxes”</em>? This is another. And it’s a Pandora’s box. I wouldn’t recommend you open it unless you want to spend a lot of time with equations and whiteboards.</p><p><strong>In AHP, setting priorities is resolved with pairwise comparisons.</strong></p><ul><li>Each participant is individually asked, “Is A or B more important, and by how much?”</li><li>After that, you review comparisons together, discuss and try to reach consensus on their values.</li><li>If consensus is not possible you can use average value and move forward.</li><li>Then, your collaboratively-agreed comparisons are translated into weights by an algorithm.</li></ul><p><strong>This is a process that is centered on collaboration and which has a mechanism that helps to eliminate deadlocks.</strong></p><h3>6. Validates consistency</h3><p>We are all humans and it’s our prerogative to be inconsistent sometimes. We make mistakes. When we make collaborative decisions there are multiple people that can make mistakes and be inconsistent. Is there any wonder so many group decisions end in deadlock and confusion?</p><p><strong>Fortunately, AHP can eliminate some of these problems. You deliver redundant data (more than needed) and an algorithm checks to see if your input is consistent.</strong></p><p>Good supporting software can then identify these inconsistencies and help you address the ones that need to be addressed.</p><h3>Good concepts stand the test of time…</h3><p>The ancient Greeks invented democracy, and it’s still the most successful system of government. But nobody today would implement it the way they did 2,000 years ago. So it is with AHP.</p><p><strong>Analytic Hierarchy Process is not the latest methodology but it is a well-proven process for collaborative decision making. It is one that is accessible to everyone and is affordable so that it can be used for decisions large-and-small.</strong></p><figure><img alt="" src="https://cdn-images-1.medium.com/max/600/1*R-saO-Xe-E1iD9PgNfcKOQ.jpeg" /><figcaption>Time for the main deal</figcaption></figure><p>RANKING OF CRITERIA <br>I chose Four attributes which are as follows:<br>1. Education<br>2. Age<br>3. Truthful<br>4. Integrity</p><p>Three alternatives were chosen for the presidential election as follows:<br>1. BUHARI<br>2. ATIKU<br>3. FelaDurotoye</p><p>check this link on how i went about with it</p><p><a href="https://github.com/galileoSolution/AHP-ASSIGNMENTS-UNILAG/blob/master/AHP%20ASSIGNMENT.ipynb">galileoSolution/AHP-ASSIGNMENTS-UNILAG</a></p><figure><img alt="" src="https://cdn-images-1.medium.com/max/640/1*P5dxUh_EPrb3wmw1V6-_kw.jpeg" /><figcaption>DONT WORRY ALMOST DONE</figcaption></figure><p>AFTER RANKING MY CRITERIA I.E THE ATTRIBUTES THIS IS WHAT I GOT ON HOW TO CHOOSE A GOOD PRESIDENTIAL CANDIDATES</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*kb75Gk3TytD-fYSe4pKwzg.jpeg" /><figcaption>THIS IS IT OO THE ATTRIBUTES OF A GOOD PRESIDENTIAL CANDIDATE</figcaption></figure><p>DONT FORGET TO CHECK MY CODES FOR MORE DETAILS</p><p>AND PLEASE GIVE IT A CLAP IF YOU LIKE IT</p><p>REGARDS</p><p>ENIOLA</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=dc77bf1d4f1c" width="1" height="1" alt=""><hr><p><a href="https://medium.com/the-data-league/analytical-hierachy-process-for-selecting-the-best-presidential-candidate-dc77bf1d4f1c">ANALYTICAL HIERACHY PROCESS FOR SELECTING THE BEST PRESIDENTIAL CANDIDATE</a> was originally published in <a href="https://medium.com/the-data-league">The Data League</a> on Medium, where people are continuing the conversation by highlighting and responding to this story.</p>]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[TEAM SOLUTION DEALING WITH REAL WORLD DATA AT DSN/ACCESS/AFF HACATHON]]></title>
            <link>https://eniolaolaleye426.medium.com/team-solution-dealing-with-real-world-data-at-dsn-access-aff-hacathon-2371ed403663?source=rss-af87cc38759c------2</link>
            <guid isPermaLink="false">https://medium.com/p/2371ed403663</guid>
            <category><![CDATA[artificial-intelligence]]></category>
            <category><![CDATA[machine-learning]]></category>
            <dc:creator><![CDATA[Eniola Olaleye]]></dc:creator>
            <pubDate>Mon, 24 Dec 2018 17:09:36 GMT</pubDate>
            <atom:updated>2018-12-28T21:06:28.859Z</atom:updated>
            <content:encoded><![CDATA[<p>TEAM SOLUTION DEALING WITH REAL WORLD DATA AT DSN/ACCESS/AFF HACATHON</p><p>TEAM SOLUTION 2ND ON THE KAGGLE LEADER-BOARD.</p><p>THE TEAM CONSISTS OF 4 MEMBERS AND AN INSTRUCTOR FROM ACCESS BANK</p><p>WE HAVE OLALEYE ENIOLA</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*yWrwteyKPgm6Sa8SUr1TdA.jpeg" /><figcaption>OLALEYE ENIOLA</figcaption></figure><p>From my prior experience with LOAN DEFAULT PREDICTION, I’ve come to appreciate that this is one of the most complex problems for applying machine learning to. Data in this domain tends to be very heterogeneous, collected over different time frames, and coming from many different sources that may change and alter in midst of the data collection process. Coming up with a proper target variable is also a very tricky process, that requires deep domain knowledge and refined business analysis skills. I want, again, to commend DATA SCIENCE NIGERIA and ACCESS BANK for coming up with such a great data , that was very amenable to Machine Learning techniques.</p><p>Based on what is known about Credit Underwriting, and in general these kinds of Machine Learning problems, it has been clear all along that there would be two things crucial for building a good model for this competition: 1. Good set of smart features. 2. Diverse set of base algorithms.</p><p>The data was huge to the extent that it made my system to malfunction for some time i had to switch to kaggle kernel which made the work very easy the munging and merging of the data was done on SQL by our instructor Mr Adewuyi Afeez.</p><p>WE discovered how efficient and easy it was to merge with SQL this made all of us in the group had interest in SQL.</p><p>We also have Chinonso Ani</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/810/1*QURsekVKAlIrHzHoB7uM7g.jpeg" /><figcaption>CHINONSO ANI</figcaption></figure><p>Chinonso helped in handling imbalanced Datasets.</p><h4>How to handle imbalanced classes</h4><p>he said</p><p>It is also important to look at the distribution of how many customers churn. If 95% of customers don’t churn, we can achieve 95% accuracy by building a model that simply predicts that all customers won’t churn. But this isn’t a very useful model, because it will never tell us when a customer will churn, which is what we are really interested in.</p><p>The class for churn is only around 25% of the total population of samples. There is a real risk that a model trained on this data may only make too many predictions in favour of the majority class. There are a number of techniques for handling imbalanced classes:</p><p>method 1:</p><h4>Up-sampling the minority class</h4><p>To balance the data set, we can randomly duplicate observations from the minority class. This is also known as re sampling with replacement:</p><p>method 2:</p><h4>Down-sampling the majority class</h4><p>Similar to the above method, we reduce the number of samples in the majority class to be equal to the number of samples in the minority class.</p><p>we also have Chuka Dean:</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*qV3TmZAVAOnnfa3Ts05kHQ.jpeg" /><figcaption>CHUKA DEAN</figcaption></figure><p>Chuka dean helped with the use of azure ml to demystify the problem.</p><p>Azure ML is built on top of the machine learning capabilities of several Microsoft products and services. It shares many of the real-time predictive analytics of the new personal assistant in Windows Phone called Cortana. Azure ML also uses proven solutions from Xbox and Bing. Outshining Nate Silver’s lauded FiveThirtyEight blog, Bing Predicts recently astonished many by <a href="http://blogs.bing.com/blog/2014/11/10/bing-gets-an-a-in-election-prediction-accuracy/">correctly forecasting the results of more than 95% of the US mid-term elections</a>. Thus, it might be worth checking out Azure ML to see what its powerful cloud-based predictive analytics can do for you.</p><p>we also have Adesiji Blessing</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*2m421kMGxz1xR4Et9nEVtw.jpeg" /><figcaption>ADESIJI BLESSING</figcaption></figure><p>Adesiji Blessing did a really good job with visualization of the Datasets.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*ohpIeIjVJ673ehsT9Et88A.jpeg" /><figcaption>CLASSIFICATION MATRIX</figcaption></figure><p>he was able to bring meaningful insights from the datas by visualizing it to know the important features.</p><p>The classification report from his work and confusion matrix are as follows:</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*W7gNYJ4Q5EOnZyUtb_Ac-g.jpeg" /><figcaption>CONFUSION MATRIX</figcaption></figure><p>Data visualization refers to presenting data in a graphical or pictorial form, such as a pie chart. This allows audiences to recognize patterns more quickly. Interactive visualizations allow decision-makers to drill down through the layers of detail. This changes perspectives so that users can review the facts behind the analysis.</p><p>Here are ways that data visualization affects decision-making and changes organizations.</p><h3>1. Faster Action</h3><p>The human brain tends to process visual information far more easily than written information. Use of a chart or graph to summarize complex data ensures faster comprehension of relationships than cluttered reports or spreadsheets.</p><p>This provides a very clear form of communication allowing business leaders to interpret and act upon their information more rapidly. Big data visualization tools can provide real-time information that’s easier for stakeholders to evaluate across the enterprise. Faster responses to market changes and quick identification of new opportunities is a competitive advantage in any industry.</p><h3>2. Communicate Findings in Constructive Ways</h3><p>Many business reports submitted to senior management are formalized documents that are often inflated with static tables and a variety of chart types. They become so elaborate that they fail to make information vibrant and memorable for those whose opinions matter most.</p><p>Reports coming from <a href="https://www.salesforce.com/hub/analytics/why-use-big-data-visualization/">big data visualization tools</a>, however, make it possible to encapsulate complex information on operational and market conditions in a brief series or even single graphic. Decision makers can easily interpret wide and varying data sources through interactive elements and new visualizations such as heat maps and fever charts. Rich but meaningful graphics help engage and inform busy executives and business partners on problems and pending initiatives.</p><p>AND finally our great instructor:</p><p>MR ADEWUYI HAFIZ</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/985/1*6EftSXCNFeo_Z3G3q9G_vA.jpeg" /></figure><p>Mr adewuyi afeez helped in merging the datasets with sql which simplified our work.</p><p>SQL stands for structured query language and is supported by a set of standards, although they seem to be implemented slightly differently by every database vendor. Even though SQL is always a little different depending on if you are using MySQL, Oracle, DB2, or whatever vendor tool you have, if you are good at writing SQL and know the database model, you can adapt quickly to get whatever data you need.</p><p>Machine learning is not new, and SQL databases are not new, so what has changed? Three things.</p><ul><li><strong>Distributed Systems: </strong>Today, SQL databases are distributed, allowing you to use more cores and have better parallelism. Overall, this enables more hardware to address a single query all at once providing the best performance. Distributed systems can scale to hundreds of servers or cloud instances, providing a different playing field of performance than single node systems.</li><li><strong>New Hardware: </strong>Modern CPU processor hardware is increasingly more sophisticated. For example, the Intel Advanced Vector Extension model, an implementation of <a href="https://link.springer.com/referenceworkentry/10.1007%2F978-0-387-78414-4_220#page-1">Single Instruction, Multiple Data</a>(SIMD) is widely available in its first iteration AVX-2 and new higher-end processors support the more advanced AVX-512. In short, SIMD allows processors to compute on multiple pieces of data simultaneously increasing parallelism at the processor level. Additionally, GPUs can achieve a similar type of parallelism by coordinating among multiple cores simultaneously.</li><li><strong>Code Generation: </strong>Code generation helps optimize queries and custom functions in a database by converting the original requests into machine code, allowing it to run much faster. However, the true power of code generation comes from generating machine code optimized for a specific query, avoiding the overhead of an interpreter. An interpreter is a piece of code, which can run any query, and as such contains more generalized instructions, which is usually not optimal for the performance of a given specific query.</li></ul><p>TOGETHER WE ARE TEAM SOLUTION THANK YOU.</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=2371ed403663" width="1" height="1" alt="">]]></content:encoded>
        </item>
    </channel>
</rss>