<?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 Data Clinic on Medium]]></title>
        <description><![CDATA[Stories by Data Clinic on Medium]]></description>
        <link>https://medium.com/@dataclinic?source=rss-bc81171ecd11------2</link>
        <image>
            <url>https://cdn-images-1.medium.com/fit/c/150/150/2*f4xCGaTzG3NQPLmfCoOTmA.png</url>
            <title>Stories by Data Clinic on Medium</title>
            <link>https://medium.com/@dataclinic?source=rss-bc81171ecd11------2</link>
        </image>
        <generator>Medium</generator>
        <lastBuildDate>Sat, 21 Nov 2026 03:30:46 GMT</lastBuildDate>
        <atom:link href="https://medium.com/@dataclinic/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[Announcing Open Source Geospatial Units in Denmark to Enable Action-Oriented Research and…]]></title>
            <link>https://medium.com/dataclinic/announcing-open-source-geospatial-units-in-denmark-to-enable-action-oriented-research-and-c46127ff3eb3?source=rss-bc81171ecd11------2</link>
            <guid isPermaLink="false">https://medium.com/p/c46127ff3eb3</guid>
            <category><![CDATA[geospatial]]></category>
            <category><![CDATA[projects]]></category>
            <category><![CDATA[data-science]]></category>
            <category><![CDATA[denmark]]></category>
            <category><![CDATA[open-source]]></category>
            <dc:creator><![CDATA[Data Clinic]]></dc:creator>
            <pubDate>Thu, 25 Aug 2022 10:14:57 GMT</pubDate>
            <atom:updated>2022-08-25T10:14:57.771Z</atom:updated>
            <content:encoded><![CDATA[<h3><strong>Announcing Open Source Geospatial Units in Denmark to Enable Action-Oriented Research and Decision-making</strong></h3><h4>Data Clinic and Aalborg University’s Department of the Built Environment (BUILD) teams are thrilled to publicly announce the <a href="https://github.com/tsdataclinic/DenmarkRegions">open source repo</a> of our work at <a href="https://foss4g.org/">FOSS4G 2022</a> in Florence.</h4><p>Data Clinic and Aalborg University’s Department of the Built Environment (BUILD) teams are thrilled to publicly announce the <a href="https://github.com/tsdataclinic/DenmarkRegions">open source repo</a> of our work, in which we built fine-grained open source geographies that facilitate actionable research and insights, today at <a href="https://foss4g.org/">FOSS4G 2022</a> in Florence. Our partnership was focused on supporting BUILD’s goal to empower data-informed action for more equitable economic opportunity across Denmark.</p><p>Over the years, the BUILD team has developed innovative insights and new metrics related to quality of life using Statistics Denmark’s fine-grained 100x100m grid level administrative data. However, they knew the true value would lie in making their actionable insights open to the public for Danish municipality decisionmakers, community organizations, and researchers alike.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/757/1*CsFBgKfNkvDEKDuPeg7AVA.jpeg" /><figcaption>The currently existing Danish boundaries: municipality borders and 100x100m grid cells</figcaption></figure><p>Until now, valuable data on the wellbeing of citizens has only been openly available at the level of large heterogeneous regions, making data-informed tailored action for urban areas vs rural areas next-to-impossible, and more granular data, which requires strong data science skills to use responsibly, is only available to select authorized agencies and researchers. BUILD set out to find the right group of stakeholders to develop and open source a new set of regions that fit right in the middle.</p><p>With the data in hand from Statistics Denmark, BUILD gathered vital financial support with a grant from data.org’s Inclusive Growth and Recovery Challenge, and connected with our team at Data Clinic to provide geospatial expertise and collaborate on the construction of these new not-too-big, not-too-small geographies — in short, the equivalent of U.S. census tracts for Denmark.</p><h4><strong>Building Socially Meaningful Polygons</strong></h4><p>Together, the Data Clinic and BUILD team aimed to step away from the 100x100m square grid. While it was computationally convenient, it didn’t reflect the world as it is today. Urban areas, neighborhoods, communities have grown and adapted to naturally occurring and people-made boundaries. Communities on one side of a wide river or a highway tend to have slightly different characteristics than those on the other side. We wanted this evolution to be reflected in the insights that BUILD eventually releases.</p><p>To develop these socially meaningful polygons, the team pulled in Denmark’s road network from Open Street Maps and municipality borders from Datafordeleren (Danish open data portal). Using a combination of existing (e.g. sf, lwgeom) and custom scripts and packages both in R and Python, we ended up with more intuitive building blocks.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/629/1*T62P80dVClh-17HGnncsaQ.png" /><figcaption>Fine-grained, socially meaningful polygons that respond to existing streets and municipality borders</figcaption></figure><h4><strong>Meeting Data Privacy Requirements Through Clustering</strong></h4><p>While we developed a more natural set of foundational polygons, we needed to then reintegrate Statistics Denmark’s 100x100m grid. The reasoning was two-fold. Firstly, as administrative data currently only exists at this grid level, the results would be immediately usable by everyone with access to it. Secondly, confirming we meet Denmark’s strict privacy requirements across all years of interest became a straightforward calculation as no interpolation or additional efforts from Statistics Denmark would be needed. Thus, we mapped the grids back onto our new polygons, assigning each grid cell to the polygon with the maximum overlap.</p><p>Making use of the Max-P regionalization algorithm from the <a href="https://pysal.org/spopt/">spopt </a>python library, and custom cluster processes, we clustered adjoining ‘gridified’ polygons until each new region represented a minimum of 100 people and a minimum of 50 households over the entire 30+ years of data that BUILD will eventually release.</p><p>With this, the Beta version of our collaboration’s granular geographies were complete.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/630/1*OKKKNHsDEtiCpsF-4L6JxQ.png" /><figcaption>The Beta regions: ‘gridified’ polygons that contain minimum 100 people and minimum 50 households</figcaption></figure><h4><strong>What’s next</strong></h4><p>There’s always room to improve methodologies, and both the BUILD and Data Clinic teams are excited to take next steps to ensure that all stakeholders find value in both these new regions and the tool BUILD is developing to publicly distribute their Danish economic prosperity metrics at this new level (slated for release in 2023).</p><p>In order to confirm or refute our hypothesis that natural and people-made boundaries would be a strong proxy for building homogenous population clusters, BUILD will proceed with spatial and longitudinal analyses to understand the variation in the regions’ characteristics.</p><p>If our new regions allow for statistically robust analyses across time and factors, our vision is that community organizations and municipality decision-makers will be able to better understand the evolution of their regions over time and make data-informed decisions on how to enable more opportunities for economic prosperity for their constituents. As we share the kinds of data that is available at this level, and the way it can be investigated through BUILD’s upcoming user-friendly tool, we are eager to incorporate these stakeholders’ feedback into all levels of the product and methodology.</p><h4><strong>Visit the Repo</strong></h4><p>We are thrilled to have the <a href="https://github.com/tsdataclinic/DenmarkRegions">open source repo</a> with the work to date now open to the public, and we look forward to receiving community feedback from our peer geospatial researchers and enthusiasts at such a seminal industry conference as FOSS4G. We invite you to contribute to the repo by reviewing, submitting issues, and commenting, or email us with questions or thoughts at dataclinic@twosigma.com.</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=c46127ff3eb3" width="1" height="1" alt=""><hr><p><a href="https://medium.com/dataclinic/announcing-open-source-geospatial-units-in-denmark-to-enable-action-oriented-research-and-c46127ff3eb3">Announcing Open Source Geospatial Units in Denmark to Enable Action-Oriented Research and…</a> was originally published in <a href="https://medium.com/dataclinic">Data Clinic</a> on Medium, where people are continuing the conversation by highlighting and responding to this story.</p>]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Scout Goes Global]]></title>
            <link>https://medium.com/dataclinic/scout-goes-global-4113dda08928?source=rss-bc81171ecd11------2</link>
            <guid isPermaLink="false">https://medium.com/p/4113dda08928</guid>
            <category><![CDATA[open-source-software]]></category>
            <category><![CDATA[open-data]]></category>
            <category><![CDATA[open-source]]></category>
            <category><![CDATA[data-for-good]]></category>
            <category><![CDATA[tech-for-good]]></category>
            <dc:creator><![CDATA[Data Clinic]]></dc:creator>
            <pubDate>Tue, 29 Mar 2022 15:10:45 GMT</pubDate>
            <atom:updated>2022-03-29T15:10:45.768Z</atom:updated>
            <content:encoded><![CDATA[<h4>Explore the potential of over 100 open data portals at your fingertips</h4><p>Two years ago, as part of <a href="https://www.open-data.nyc/">NYC Open Data Week</a>, we <a href="https://medium.com/dataclinic/data-clinic-unveils-latest-open-source-tool-during-nyc-open-data-week-3207a585490c">unveiled Scout</a>, our open source data discoverability tool to explore New York City’s <a href="https://data.cityofnewyork.us/browse">open data portal</a>. <a href="https://scout.tsdataclinic.com/">Scout</a> allows you to search for open datasets and recommends other datasets that might be relevant to you. The tool also surfaces thematically similar datasets as well as datasets that have joinable columns that can enrich the dataset you are looking at.</p><p>The launch of Scout was met with excitement from the local open data community, but we knew that this was just scratching the surface of what was possible. There is a lot more data out there and the data needs of researchers typically go well beyond a single city. As part of NYC Open Data Week 2022, we unveiled the newest update to Scout: a multi-portal approach to data discoverability. The update allows Scout users to explore 129 portals across the world hosting over 125,000 datasets, and analyze relationships across more than 1.2 million columns.</p><figure><img alt="A screengrab of scout: a listing of NYC-related datasets and their descriptions under a drop-down menu to select any available open data portal to peruse" src="https://cdn-images-1.medium.com/max/1024/0*8dDYMhLQSZsmP7By" /><figcaption><em>The new portal dropdown allows users to select specific data portals.</em></figcaption></figure><p>Scout now includes a portal selector dropdown where you can choose which open data portal you want to explore. In the top-right you can also toggle between exploring a single portal or looking at <em>all</em> available data portals. At the moment, Scout wraps the <a href="https://dev.socrata.com/">Socrata API</a>, so the tool is limited to Socrata-hosted data portals. As part of our future roadmap we intend to expand this to include more open data management systems, such as <a href="https://ckan.org/">CKAN</a> and <a href="https://www.esri.com/en-us/arcgis/products/arcgis-open-data">ESRI</a>.</p><p>In addition to multi-portal support, existing Scout features were updated to improve the user experience.</p><figure><img alt="Another screen grab of Scout showing a list of datasets and their descriptions under a pop-up ‘sign in’ modal that provides options to make an account or sign in using Google or Facebook" src="https://cdn-images-1.medium.com/max/1024/0*LwJVd1NKS-GpmXa2" /><figcaption><em>Users can now log in to Scout using existing social media accounts or with their email and a unique password.</em></figcaption></figure><p>Scout now supports user authentication that allows you to create a user account either through an existing social media account (Facebook or Google) or with your own email and password combination. This feature allows you to keep your curated collections forever by linking them to your user account. We do not track your searches or your personal information beyond what is absolutely necessary for you to log in. If you prefer to continue using Scout without logging in, you can still do so and have access to all of Scout’s search features. However, without logging in, you would lose your stored collections when you clear your browser cache or switch computers.</p><figure><img alt="A screengrab of Scout that shows a description of the data in the left-hand section, and the list of GitHub commits and repos that use that same data in the right-hand section" src="https://cdn-images-1.medium.com/max/1024/0*BrGLgKvk1_ARiYWk" /><figcaption><em>The new resources tab provides examples of how the dataset has been previously utilized.</em></figcaption></figure><p>This newest update also includes a resources tab that displays examples of a dataset’s usage that can help guide researchers in understanding how the dataset can be applied and explore how it has been previously used. We hope this feature will facilitate collaborations and accelerate innovation by showcasing past work that can be built upon and limiting redundant analyses.</p><p>In the future, we hope to incorporate blog posts that mention the data to the resources tab to continue to build a library of inspiration for users. We also see a lot of potential in enabling users to submit their own helpful resources directly into Scout.</p><p>We are excited to see how this new iteration of Scout can help open data researchers find helpful datasets that extend beyond their local communities. We encourage you to check out and share any feedback you have with us as we continue to beta test this tool. If you find any bugs, please open a <a href="https://github.com/tsdataclinic/scout/issues">GitHub issue</a> for us to address.</p><p>We also encourage you to open a <a href="https://github.com/tsdataclinic/scout/discussions">GitHub discussion</a> with any feature ideas or contribute by <a href="https://github.com/tsdataclinic/scout">cloning our repo</a>. Our repo contains instructions on setting up Scout locally and contributing to its codebase. We are actively working to improve Scout and would love to have you involved.</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=4113dda08928" width="1" height="1" alt=""><hr><p><a href="https://medium.com/dataclinic/scout-goes-global-4113dda08928">Scout Goes Global</a> was originally published in <a href="https://medium.com/dataclinic">Data Clinic</a> on Medium, where people are continuing the conversation by highlighting and responding to this story.</p>]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[The Hidden Stories of New York as Told Through Open Data]]></title>
            <link>https://medium.com/dataclinic/the-hidden-stories-of-new-york-as-told-through-open-data-68081d595763?source=rss-bc81171ecd11------2</link>
            <guid isPermaLink="false">https://medium.com/p/68081d595763</guid>
            <category><![CDATA[data-science]]></category>
            <category><![CDATA[data-clinic]]></category>
            <category><![CDATA[data]]></category>
            <category><![CDATA[new-york-city]]></category>
            <category><![CDATA[open-data]]></category>
            <dc:creator><![CDATA[Data Clinic]]></dc:creator>
            <pubDate>Thu, 03 Mar 2022 22:53:00 GMT</pubDate>
            <atom:updated>2022-03-08T18:50:58.361Z</atom:updated>
            <content:encoded><![CDATA[<h4>Data Clinic reflects on some of our favorite NYC Open Data projects to celebrate NYC Open Data Week 2022</h4><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*dRFgBthjr5xPflCYrPftYA.png" /></figure><p>Founded in downtown Manhattan in 2001, Two Sigma and much of its community are proud to call New York City home. Our history is intertwined with the city’s and we recognize how much we owe to the place where we laid our foundation. Our Data Clinic team has worked hand-in-hand with <a href="https://airtable.com/shrwBoVEJ6nOuKUFh">partners </a>throughout the city to give back to our community for a number of years, but more recently has begun to build tools to uncover the hidden stories and insights that exist within the city’s open data. As we join our fellow open data enthusiasts at <a href="https://www.open-data.nyc/">NYC Open Data Week</a>, we reflect back on some of these efforts and the opportunities they offer to empower the NYC community:</p><h3>Subway Accessibility</h3><p>Inspired by the <a href="https://www.un.org/en/observances/day-of-persons-with-disabilities">International Day of Persons with Disabilities</a>, Data Clinic hosted a hackathon on the <a href="https://github.com/tsdataclinic/mta">NYC Subway system’s accessibility</a>. Data Clinic volunteers built subway station maps, cleaned turnstile data, and developed a vital naming convention crosswalk to better understand NYC subway elevator accessibility. <a href="https://medium.com/dataclinic/open-tools-to-analyze-accessibility-within-the-nyc-subway-system-383fb111b4ad?source=collection_category---4------6-----------------------">Read more</a>.</p><h3>Reimagining NYC Neighborhoods</h3><p>NYC’s neighborhoods are a driving force in the lives of New Yorkers — their identities are closely intertwined and a source of pride. However, the history and evolution of NYC’s neighborhoods don’t follow the rigid, clinical lines of statistical and administrative boundaries that are often used to identify them. From a statistical standpoint, grouping and analyzing data at these administrative boundary levels may not be ideal for analysis. The Data Clinic team therefore developed <a href="https://data-clinic.shinyapps.io/newerhoods/">NewerHoods </a>to reflect the conceptual and statistical benefits of using a data-driven approach to identifying neighborhoods. <a href="https://medium.com/dataclinic/reimagining-nyc-neighborhoods-through-open-data-35e0549a9750">Read more</a>.</p><h3>Bullying in NYC Schools</h3><p>As part of Open Data Week 2018, the Data Clinic team hosted a “<a href="https://github.com/tsdataclinic/open-data-week">State of Open Data on School Bullying and Harassment</a>” event, which featured a comparative analysis of federal and local datasets, followed by a panel discussion on what open data can reveal — and conceal — about this important school safety issue. Notably, the team showed that fewer than a quarter of the city’s 1,700+ public and charter schools reported a single incident of bullying or harassment to the US Department of Education’s Office for Civil Rights in a given year. <a href="https://www.twosigma.com/articles/data-clinic-what-we-learned-from-open-data-on-bullying-and-harassment-in-nyc-schools/">Read more</a>.</p><h3>Subway Ridership Trends</h3><p>NYC’s subway system is the heartbeat of the city, shifting millions of people between their homes, schools, and workplaces each day. Although the pandemic altered much of city life, the subway system continued to provide transportation to those who still needed to go into work everyday. The Data Clinic team used our open source tool <a href="https://subwaycrowds.tsdataclinic.com/">SubwayCrowds </a>to estimate subway crowdedness and create visualizations of the average weekday ridership numbers during the pandemic at different stops over the course of a day. <a href="https://medium.com/dataclinic/commuting-during-covid-19-identifying-subway-ridership-trends-dfcf2492d03e?source=collection_category---4------2-----------------------">Read more</a>.</p><h3>New York City’s Loudest Holiday</h3><p>From spectacular fireworks on the 4th of July to the crowds of Time Square on New Year’s Eve, New York City knows how to throw a party — especially when people have a few days off! The Data Clinic team <a href="https://github.com/tsdataclinic/NY311HolidayComplaints">dove into the open data</a> to determine what holiday does New York City celebrate the most. <a href="https://medium.com/dataclinic/new-york-citys-loudest-holiday-according-to-open-data-df35e79ac4fa?source=collection_category---4------5-----------------------">Read more</a>.</p><h3>Get Involved</h3><p>We look forward to continuing to build tools and share analyses that provide our beloved city with opportunities to continue to grow and lift up members of our community. Visit the <a href="https://github.com/tsdataclinic">Data Clinic GitHub</a> to learn more about and contribute to these open source projects and more.</p><p>To join our NYC Open Data Week workshop this Thursday March 10th from 11am-12pm ET in which we’ll unveil the latest features of our open source <a href="https://scout.tsdataclinic.com/">open data discovery tool scout</a>, RSVP here: <a href="https://2022.open-data.nyc/event/eureka-discovering-open-data-with-scout-multicity/#rsvp-now">https://2022.open-data.nyc/event/eureka-discovering-open-data-with-scout-multicity/#rsvp-now</a></p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=68081d595763" width="1" height="1" alt=""><hr><p><a href="https://medium.com/dataclinic/the-hidden-stories-of-new-york-as-told-through-open-data-68081d595763">The Hidden Stories of New York as Told Through Open Data</a> was originally published in <a href="https://medium.com/dataclinic">Data Clinic</a> on Medium, where people are continuing the conversation by highlighting and responding to this story.</p>]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[2021: A Year in Review]]></title>
            <link>https://medium.com/dataclinic/2021-a-year-in-review-149c7ae57a8d?source=rss-bc81171ecd11------2</link>
            <guid isPermaLink="false">https://medium.com/p/149c7ae57a8d</guid>
            <category><![CDATA[tech-for-good]]></category>
            <category><![CDATA[corporate-culture]]></category>
            <category><![CDATA[data-for-good]]></category>
            <category><![CDATA[social-impact]]></category>
            <category><![CDATA[data-clinic]]></category>
            <dc:creator><![CDATA[Data Clinic]]></dc:creator>
            <pubDate>Fri, 14 Jan 2022 14:02:36 GMT</pubDate>
            <atom:updated>2022-01-14T14:02:36.086Z</atom:updated>
            <content:encoded><![CDATA[<h4>Taking a moment to reflect back on Data Clinic’s year in data- and tech-for-good</h4><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*Wbp9n_21vEspACZtqpzSKw.png" /></figure><p>It’s hard to believe another year has flown by. Despite the ongoing pandemic, our team continues to adapt and find new ways to support mission-driven organizations, collaborate with peers, and contribute to learning communities. Overall, it was a great year thanks to the hard work and dedication of our partners, volunteers, and colleagues. Read on for a brief look back at some of our 2021 highlights as we gear up for another wonderful year of data and tech for social good.</p><h4>Open source</h4><ul><li>We released an<a href="https://medium.com/dataclinic/building-a-survey-tool-that-strikes-a-balance-between-customization-and-ease-of-use-c180784c5eb8?source=collection_category---4------0-----------------------"> interview library </a>that allows the developer to have greater flexibility and control in setting up data collection survey tools, and includes several accessibility features for respondents with lower literacy levels.</li><li>We updated our <a href="https://github.com/tsdataclinic/mta">MTA subway repository</a> with more up-to-date graphs of accessible stations</li><li>We improved our analysis on <a href="https://medium.com/dataclinic/commuting-during-covid-19-identifying-subway-ridership-trends-dfcf2492d03e?source=collection_category---4------2-----------------------">crowding in the NYC subway</a> during the pandemic to see how foot traffic compared to the previous year</li></ul><figure><img alt="" src="https://cdn-images-1.medium.com/max/462/1*ftmS9R_J1oE1yxE_nIvWcA.jpeg" /><figcaption>A sample heat map of crowding at NYC Subway stations during COVID</figcaption></figure><h4>Projects</h4><ul><li>We collaborated with the <a href="https://medium.com/dataclinic/building-an-interactive-dashboard-to-support-decision-makers-for-covid-19-in-africa-7d458cb2bac6?source=collection_category---4------1-----------------------">COVID-19 in Africa Data Science</a> team to build a Africa-focused dashboard that shows the latest stats for COVID on the continent and facilitates access to the team’s insights</li><li>In partnership with <a href="https://medium.com/dataclinic/a-marine-plastics-identification-problem-with-a-ml-solution-b9af3d9cf867?source=collection_category---4------2-----------------------">Plymouth Marine Laboratory</a>, we released an open source package for detecting macro plastics in the ocean using satellite imagery</li><li>We wrapped two partnerships with the <a href="https://medium.com/dataclinic/applying-data-science-to-optimize-stem-cell-production-b1f1ef9ab169">New York Stem</a> <a href="https://medium.com/dataclinic/building-a-cell-visualization-tool-to-meet-the-expanding-needs-of-the-new-york-stem-cell-foundation-f8af0392ab78">Cell Foundation Research</a> Institute to support the optimization of work related to the production of induced pluripotent stem cells (iPSCs)</li><li>We supported <a href="https://medium.com/dataclinic/using-data-to-expand-equitable-arts-programming-in-nashville-34a1e514f37?source=collection_home---4------0-----------------------">Nashville Metro Arts</a> in uncovering data-driven insights on equitable access to their varied arts programming across the county</li><li>We kicked off a partnership with Aalborg University, <a href="https://data.org/initiatives/challenge/build-aalborg-university/">one of data.org’s Inclusive Growth and Recovery Challenge winners</a>, to create regions within Denmark that allow for more informative and user-friendly data sharing with decision-makers</li><li>As part of one of our internal Hack Days, we built a proof-of-concept version of an interactive map for <a href="https://github.com/tsdataclinic/UIC-MMIP-Policy-Tracker">Urban Indigenous Collective</a>’s Missing and Murdered Indigenous Peoples Policy Tracker so users could have a visual alternative for exploring their database</li></ul><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*guQNQnb-Z1SPprXac6uvww.jpeg" /><figcaption><em>Ghost Ballet for the East Bank Machineworks in Nashville. </em>Artist: Alice Aycock, Photographer: Gary Layda</figcaption></figure><h4>Events</h4><ul><li>We kicked off our new workshop series: <a href="https://medium.com/dataclinic/good-with-numbers-e688365e7bf3">Good with Numbers</a>. These free, small-format workshops aim to equip nonprofits with actionable tips to build data strategies and make data more valuable for their teams. <a href="https://www.eventbrite.com/o/data-clinic-34064114261">Follow us on Eventbrite</a> to be alerted to new sessions</li><li>We also launched our free virtual open office hours series, in which nonprofits can stop by without an appointment to pose specific data challenges to Data Clinic staff for technical and/or strategic guidance. <a href="https://www.eventbrite.com/o/data-clinic-34064114261">Follow us on Eventbrite</a> to be alerted to new sessions</li></ul><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*DVDafOleSIVys_yfgUUUIQ.png" /></figure><h4>Conferences and media</h4><ul><li>NYC Open Data Week: Kaushik Mohan presented <a href="https://www.youtube.com/watch?v=tlDyxxO1sSk"><em>Commuting during COVID-19: using open data to predict NYC Subway crowds</em></a></li><li>Good Tech Fest: Kaushik Mohan presented <a href="https://www.youtube.com/watch?v=Ul1q0jgnK8Q"><em>Shifting from Equality to Equity Through Responsible Data Use</em></a>, and Erin Stein presented <a href="https://www.youtube.com/watch?v=JggC870tnPY"><em>Tips for Successful Cross-Sector Partnerships in Data and Tech</em></a></li><li>Social Innovation Summit: Rachael Weiss Riley participated on the panel <a href="https://www.youtube.com/watch?v=ZX5mKBtzpC0"><em>Data-Driven through an Equity Lens</em></a></li><li>The Tech for Good Bulletin shone a spotlight on Data Clinic’s story and how we work: <a href="https://www.techforgood.net/mag/techforgood-september-2021"><em>Driving Equity through Data</em></a></li><li>Nuance of Impact: Rachael Weiss Riley sat down with Rebecca Nedelec to talk about <a href="https://podcasts.apple.com/us/podcast/s2-ep6-the-stories-that-live-behind-data-rachael/id1514717834?i=1000540001042"><em>The Stories that Live Behind Data</em></a></li></ul><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*pDI8aPVp4laPnBF6Gx29Ew.jpeg" /><figcaption>Data Clinic Director Rachael Weiss Riley (bottom left) at the Social Innovation Summit</figcaption></figure><h4>Peer collaboration</h4><ul><li>Alongside all our peers in the Tech for Good Symposium, we are eager to share the <a href="https://airtable.com/shr37qFKRWQ9hUulY/tblPHOLLpA2YZ0lTV">Data and Tech for Good landscape</a> database. This is a living document categorizing and detailing member companies’ data- and tech-for-good initiatives, alongside contact information to learn more. We hope this resource will inspire learnings, new initiatives, and collaboration both across the for-profit sector, and between the for-profit and social impact sector.</li></ul><p>Our teams are already hard at work on some exciting projects for 2022, and we look forward to sharing more with you. If you’re interested in collaborating with us on a partnership, <a href="https://airtable.com/shrwBoVEJ6nOuKUFh">please fill out this interest form</a>, and if you’d like to contribute to any of our open source projects, <a href="https://github.com/tsdataclinic">please check out our repos on GitHub</a>. For all other questions or ideas, you can reach us at <a href="/service/mailto:dataclinic@twosigma.com">dataclinic@twosigma.com</a>.</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=149c7ae57a8d" width="1" height="1" alt=""><hr><p><a href="https://medium.com/dataclinic/2021-a-year-in-review-149c7ae57a8d">2021: A Year in Review</a> was originally published in <a href="https://medium.com/dataclinic">Data Clinic</a> on Medium, where people are continuing the conversation by highlighting and responding to this story.</p>]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Data and Tech for Good Landscape]]></title>
            <link>https://medium.com/dataclinic/data-and-tech-for-good-landscape-eee7626ea36d?source=rss-bc81171ecd11------2</link>
            <guid isPermaLink="false">https://medium.com/p/eee7626ea36d</guid>
            <category><![CDATA[data-clinic]]></category>
            <category><![CDATA[data-for-good]]></category>
            <category><![CDATA[corporate-culture]]></category>
            <category><![CDATA[social-impact]]></category>
            <category><![CDATA[tech-for-good]]></category>
            <dc:creator><![CDATA[Data Clinic]]></dc:creator>
            <pubDate>Wed, 12 Jan 2022 21:58:26 GMT</pubDate>
            <atom:updated>2022-01-12T21:58:26.165Z</atom:updated>
            <content:encoded><![CDATA[<h4>The Tech for Good Symposium launches a living document to ease collaboration within and across the data- and tech-for-good sector</h4><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*NfB6BTzyHp1cvy45fZMT3w.jpeg" /><figcaption>The Data and Tech for Good Landscape produced by the Tech for Good Symposium</figcaption></figure><p>The data- and tech-for-good sector, while fairly established at this point, is still rapidly expanding. While this has its advantages: more and varied offerings for support, new technologies and methodologies for more robust solutions, etc. — it can make staying abreast of the latest trends and finding the right support for your needs a challenge.</p><p>We’re thrilled to be a co-lead and active member of the Tech for Good Symposium, a network of Tech and Data for Good practitioners that are using their technology and data resources and skills to address issues in the communities where we live and work. Through the Symposium, our sector shares best practices and uncovers opportunities to collaborate on an ongoing basis.</p><p>In the spirit of our mission of contributing knowledge to the broader social impact sector, we are eager to share the<a href="https://airtable.com/shr37qFKRWQ9hUulY/tblPHOLLpA2YZ0lTV"> Data and Tech for Good landscape</a> database. This is a living document categorizing and detailing member companies’ data- and tech-for-good initiatives, alongside contact information to learn more. In it, you’ll find a variety of programs, such as partnerships with nonprofits, hackathons for students and job seekers, and compute credits for researchers. Think of it as a “yellow pages” for data- and tech-based supports from for-profit organizations.</p><p>It is our hope that<a href="https://airtable.com/shr37qFKRWQ9hUulY/tblPHOLLpA2YZ0lTV"> this landscape</a> will inspire learnings, new initiatives, and collaboration both across the for-profit sector, and between the for-profit and social impact sectors. If you have any feedback or suggestions for the landscape, or to learn more about the Tech for Good Symposium, please email <a href="/service/mailto:techforgoodsymposium@gmail.com">techforgoodsymposium@gmail.com</a>.</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=eee7626ea36d" width="1" height="1" alt=""><hr><p><a href="https://medium.com/dataclinic/data-and-tech-for-good-landscape-eee7626ea36d">Data and Tech for Good Landscape</a> was originally published in <a href="https://medium.com/dataclinic">Data Clinic</a> on Medium, where people are continuing the conversation by highlighting and responding to this story.</p>]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Building a Cell Visualization Tool to Meet the Expanding Needs of the New York Stem Cell Foundation]]></title>
            <link>https://medium.com/dataclinic/building-a-cell-visualization-tool-to-meet-the-expanding-needs-of-the-new-york-stem-cell-foundation-f8af0392ab78?source=rss-bc81171ecd11------2</link>
            <guid isPermaLink="false">https://medium.com/p/f8af0392ab78</guid>
            <category><![CDATA[health]]></category>
            <category><![CDATA[engineering]]></category>
            <category><![CDATA[projects]]></category>
            <category><![CDATA[medicine]]></category>
            <category><![CDATA[technology]]></category>
            <dc:creator><![CDATA[Data Clinic]]></dc:creator>
            <pubDate>Tue, 11 Jan 2022 21:25:35 GMT</pubDate>
            <atom:updated>2022-01-11T21:25:35.788Z</atom:updated>
            <content:encoded><![CDATA[<h4>Data Clinic partnered with the New York Stem Cell Foundation (NYSCF) to optimize and enhance a critical piece of software used in conjunction with the <a href="http://nyscf.org/research-institute/global-stem-cell-array/">NYSCF Global Stem Cell Array®</a></h4><figure><img alt="Stem cell-derived retinal pigmented epithelial cells. The cell walls are bright green, and filled with pinks and blues. Image credit: Cecile Terrenoire, PhD" src="https://cdn-images-1.medium.com/max/627/1*ooL8evDgVH81M0YkC_TeQg.jpeg" /><figcaption>Stem cell-derived retinal pigmented epithelial cells. Image credit: Cecile Terrenoire, PhD</figcaption></figure><h4>Data Clinic’s history of using data to do good</h4><p>As Two Sigma’s pro bono data- and tech-for-good initiative, we help mission-driven organizations use their data and tech more effectively. While most of our projects have been research-focused with some lighter-weight tooling supports, we launched our first deeply collaborative engineering engagement in close concert with our friends at the <a href="https://www.nyscf.org/">New York Stem Cell Foundation</a> (NYSCF) the summer of 2020. NYSCF, a nonprofit organization whose mission is to accelerate new treatments and cures for patients, is an innovative engineering partner engaged in large-scale, robust, and cutting-edge science.</p><p>Data Clinic’s relationship with NYSCF began in 2019, thanks to an introduction from Alfred Spector, Two Sigma’s retired CTO who also serves as a Senior Scientific Advisor to NYSCF on various programs. Data Clinic and NYSCF first partnered on a data science project to improve the workflow of the <a href="http://nyscf.org/research-institute/global-stem-cell-array/">NYSCF Global Stem Cell Array® (TGSCA™)</a>: a unique, fully automated platform for the production, expansion, gene editing, and differentiation of stem cells (you can read about this project <a href="https://docs.google.com/document/d/13uKCKkMeqZ39S7bO46_VU0zioQlQ6MdCWW-HjJ_t4PM/edit">here</a>). On the heels of this successful collaboration, a new team of Data Clinic volunteers came together for an engineering-based project to optimize a critical piece of software researchers use in conjunction with the TGSCA™.</p><h4>Advancing medical research with microscopic images of cells</h4><p>The NYSCF Research Institute, an independent laboratory, is a non-profit accelerator that bridges the gap between research institutions and pharmaceutical and biotech companies by reducing the cost, time, and risk that historically inhibit the development of new treatments and cures. Since its founding in 2005, NYSCF has shed light on conditions including Alzheimer’s disease, diabetes, macular degeneration, multiple sclerosis, Parkinson’s disease, and COVID-19.</p><p>The NYSCF Global Stem Cell Array® is capable of deriving hundreds of induced pluripotent stem cell (iPSC) lines per month, a process in which NYSCF researchers revert donated skin or blood samples into a stem cell state. These are used to study the disease by turning the iPSCs into cells such as neurons, cardiomyocytes (heart cells), and hepatocytes (liver cells). NYSCF has generated iPSC lines from various cohorts, including <a href="https://www.cell.com/neuron/fulltext/S0896-6273(21)00578-X">Alzheimer’s disease</a> and <a href="https://www.nei.nih.gov/about/goals-and-accomplishments/nei-research-initiatives/regenerative-medicine/amd-integrative-biology-initiative">macular degeneration</a>, with these cell lines available to the research community through the <a href="https://www.nyscf.org/research-institute/repository-stem-cell-search/">NYSCF Repository</a>.</p><figure><img alt="In a lab setting with machinery and desks, we see one man standing on the left working on a computer, one person in the middle sitting at a desk in a white lab coat working on a computer, and one person to the right hunched over a desk." src="https://cdn-images-1.medium.com/max/1024/1*a1krj2BgUeyE45wexASNRQ.png" /><figcaption>Scientists at work on the NYSCF Global Stem Cell Array®</figcaption></figure><p>“The Data Clinic team has done outstanding work with our researchers in optimizing aspects of our data-analysis pipeline, and now working together on an engineering-focused project has been terrific,” said Dan Paull, PhD, SVP of Discovery and Platform Development at NYSCF. “This project has not only benefited our researchers, providing them a valuable tool for interacting with our data, but has given our software engineers a chance to draw on the experience of the talented developers at Two-Sigma. We are incredibly grateful for their amazing pro bono help, and I’m looking forward to what we will accomplish together.”</p><p>A fundamental component of the NYSCF workflow is growing wells of cells, examining images of these cells, and making decisions based on their morphology and growth. When stem cells are generated for use in disease research, it can be important from a quality control perspective to be sure that each sample of cells arises from a single ‘clone’ or single cell. While cell wells are imaged daily, commercially available tools designed to aid in reviewing ‘clonality’ were slow to respond, severely limiting NYSCF researchers’ bandwidth. Taking advantage of NYSCF’s expansive imaging dataset, data scientists at the foundation developed a deep learning framework (<a href="https://nyscf.org/open-source/monoqlo/">Monoqlo℠</a>) for automatically detecting the clonality of cell colonies based on the automated images of the cells captured daily (<a href="https://www.nature.com/articles/s42256-021-00354-7?proof=t">published in Nature Machine Intelligence</a>). Building upon this, NYSCF had developed a tool for visualizing the results and images derived from Monoqlo℠; however, as its usage increased, the functional requirements of the tool exceeded NYSCF’s engineering bandwidth. Therefore, the goal of Data Clinic’s involvement was to optimize the tool to make things run faster, add features to track and annotate cell wells, and align the underlying codebase closer to that of NYSCF’s growing web apps.</p><h4>Improving NYSCF’s cell visualization tool</h4><p>In the new Visualization Tool (VisTool), NYSCF researchers can view the clonality call and class of each cell well on a given plate, load and view images of each cell well over time, and flag specific wells for further review. Thanks to optimization around image loading, the time required to view hundreds of wells was drastically reduced, with researchers now able to review data over 16 times faster. Amongst other logistical benefits, collaborating with the new tool is also substantially easier, since researchers can now simply share a link to any screen within the tool.</p><figure><img alt="Neurons derived from the stem cells of a Parkinson’s patient. The neurons are colored bright yellow against a black background and resemble thin strands of hair. Image credit: Angelique Di Domenico, PhD" src="https://cdn-images-1.medium.com/max/623/1*d9U-h3qov5PssrxEG6XzlA.png" /><figcaption>Neurons derived from the stem cells of a Parkinson’s patient. Image credit: Angelique Di Domenico, PhD</figcaption></figure><h4>Development principles</h4><p>The Data Clinic engineering team aimed to build a tool easy to maintain and extend. This meant keeping the codebase easily readable for new developers and using a component-based design that could be reused for other similar workflows. The collaborative group tackled several specific technical queries from this mandate.</p><h4>The future</h4><p>We look forward to seeing how the time saved through this more efficient cell monitoring tool will be spent on doing impactful research. We’re also thrilled to seek out new engineering-based collaborations based on our successes in this space thus far.</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=f8af0392ab78" width="1" height="1" alt=""><hr><p><a href="https://medium.com/dataclinic/building-a-cell-visualization-tool-to-meet-the-expanding-needs-of-the-new-york-stem-cell-foundation-f8af0392ab78">Building a Cell Visualization Tool to Meet the Expanding Needs of the New York Stem Cell Foundation</a> was originally published in <a href="https://medium.com/dataclinic">Data Clinic</a> on Medium, where people are continuing the conversation by highlighting and responding to this story.</p>]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Applying Data Science to Optimize Stem Cell Production]]></title>
            <link>https://medium.com/dataclinic/applying-data-science-to-optimize-stem-cell-production-b1f1ef9ab169?source=rss-bc81171ecd11------2</link>
            <guid isPermaLink="false">https://medium.com/p/b1f1ef9ab169</guid>
            <category><![CDATA[data-science]]></category>
            <category><![CDATA[health]]></category>
            <category><![CDATA[projects]]></category>
            <category><![CDATA[data]]></category>
            <category><![CDATA[medicine]]></category>
            <dc:creator><![CDATA[Data Clinic]]></dc:creator>
            <pubDate>Tue, 11 Jan 2022 21:23:49 GMT</pubDate>
            <atom:updated>2022-01-11T21:23:49.066Z</atom:updated>
            <content:encoded><![CDATA[<h4>Data Clinic recently partnered with the New York Stem Cell Foundation Research Institute (NYSCF) to optimize their innovative approach to producing <a href="https://nyscf.org/stem-cell-basics/what-are-stem-cells/#:~:text=Induced%20pluripotent%20stem%20cells%20(iPSCs)%20are%20stem%20cells%20created%20through,a%20Nobel%20Prize%20for%20Medicine">induced pluripotent stem cells</a></h4><p>Our team strives to enhance the role of the human in the loop at every partner organization — not replace them. We applied this approach during our recent collaborations with the New York Stem Cell Foundation Research Institute (NYSCF) to assist the foundation in using data science to optimize their innovative approach to producing <a href="https://nyscf.org/stem-cell-basics/what-are-stem-cells/#:~:text=Induced%20pluripotent%20stem%20cells%20(iPSCs)%20are%20stem%20cells%20created%20through,a%20Nobel%20Prize%20for%20Medicine">induced pluripotent stem cells</a> (iPSCs).</p><figure><img alt="Stem cell-derived neurons in purple and yellow on a black vbackground. Image credit: Barry McCarthy" src="https://cdn-images-1.medium.com/max/516/1*xcIqumNYtJ88_lUE-xehCg.png" /><figcaption>Stem cell-derived neurons. Image credit: Barry McCarthy</figcaption></figure><h4><strong>A laboratory at the forefront of innovative disease treatment</strong></h4><p><a href="https://nyscf.org/">NYSCF</a> is an independent nonprofit organization that seeks to “accelerate cures for the major diseases of our time through stem cell research.” In particular, NYSCF focuses on the production and use of iPSCs. These cells, which can be grown from anyone’s donated blood or skin samples, can be converted into any of the 200+ types of cells in our bodies, providing valuable, individualized material for research and testing disease treatments.</p><p>NYSCF has developed an innovative robotic system to produce iPSCs on a large scale: the<a href="http://nyscf.org/research-institute/global-stem-cell-array/"> NYSCF Global Stem Cell Array® (TGSCA™)</a>. The ability to produce iPSCs in such quantities is invaluable, not only in helping NYSCF conduct innovative medical research, but enabling others through the distribution of these cell lines through the <a href="https://nyscf.org/research-institute/repository-stem-cell-search/">NYSCF Repository</a>. NYSCF has generated large panels of cell lines spanning diseases including <a href="https://www.cell.com/neuron/fulltext/S0896-6273(21)00578-X">Alzheimer’s</a>, <a href="https://www.nei.nih.gov/about/goals-and-accomplishments/nei-research-initiatives/regenerative-medicine/amd-integrative-biology-initiative">macular degeneration</a>, and rare diseases. At any given time, NYSCF is processing hundreds to thousands of samples in parallel culture, 10–100X the capability you would find in most other research laboratories.</p><h4><strong>Humans in the loop</strong></h4><p>While most of the TGSCA™ is automated, there is a vital review process between experiment stages to determine if plates of cell cultures are ready to enter the next step in the cell culture process. Until now, this work has required up to an hour each day from a scientist to review the data and make a judgment call based on their expertise and experience as to whether the plate is ready to continue passaging.</p><p>“If I am working, I am going to make one set of decisions. Then the next weekend, someone else will be here and they’ll make another set of decisions,” said Daniel Paull, PhD, NYSCF Senior Vice President of Discovery and Platform Development. “If we can have a tool that guides decision-making in a very standardized way, that will reduce the variation and perhaps increase our efficiencies as well as the quality of all of the cell lines that we make.”</p><figure><img alt="Six scientists in white lab coats huddle around a computer screen to examine cells generated by the NYSCF Global Stem Cell Array®" src="https://cdn-images-1.medium.com/max/1024/1*DIUH4wgq-uaY7N5oCkYMRA.jpeg" /><figcaption>Scientists huddle to examine cells generated by the NYSCF Global Stem Cell Array®</figcaption></figure><p>Additionally, on a practical level, machine availability is a crucial consideration when producing stem cells at scale, meaning any use of the robots must be carefully and strategically planned. Biology often has its own ideas on timing, however, and the rate at which cells grow can be highly variable.</p><p>To make these processes more efficient, NYSCF began working towards a single machine learning model or “oracle” that could serve as a centralized source of future state prediction and sought to determine whether such a tool could be built from its vast repository of historical data. The organization rigorously collects a rich set of biological and logistical data points during the cell culturing process, including the amount of time cells spend growing, the environmental conditions and hardware specifications during each sample processing.</p><h4><strong>The ask</strong></h4><p>NYSCF had begun exploring the concept of the optimal time to “passage” (transfer) cells at the individual well-level, developing an initial approach to predicting potential well transfer times in half-day increments. To continue this work that was first developed by students in the NYSCF internship program, NYSCF approached Data Clinic for data science support.</p><p>NYSCF’s initial asks were two-fold:</p><ul><li>Could we identify ideal characteristics of plates ready for passage?</li><li>Can we use that information to predict the optimal time for passage several days in advance?</li></ul><p>“The Data Clinic team is doing outstanding work with our researchers to optimize our studies, and it is a true testament to the power of data science for improving research, and in turn, outcomes for patients,” noted Rick Monsma, PhD, NYSCF Senior Vice President of Scientific Operation. “Understanding when to optimally passage cells also gives scientists back a bit of their most valuable asset: their time. We were excited to hit the ground running on this project with Two Sigma, and we have already learned a great deal thanks to their outstanding models and commitment to collaboration.”</p><h4><strong>Data challenges</strong></h4><p>As with any project, we spent a lot of time with the engaged team at NYSCF, getting to know the extraordinary work they do and how they do it. We needed to understand the lifecycle of the samples/plates throughout the TGSCA™, the tasks and roles of the researchers, how this work fits into NYSCF’s bigger picture, and what data is collected and when throughout the process.</p><p>When considering the characteristics of plates passaged at the ideal time, we needed to have ground truth or a “set of truth.” Defining criteria around the optimal time to passage cells allowed us to delve into datasets measured in the millions of rows that NYSCF had robustly and uniformly collected since early 2013.</p><figure><img alt="Oligodendrocytes derived from a multiple sclerosis patient. The Oligodendrocytes are light blue and yellow specks scattered about a black background, almost resembling a densely starry night sky. Image credit: Maria Sapar, PhD" src="https://cdn-images-1.medium.com/max/427/1*tryYeMmPVw33Y-9wSBKmgQ.jpeg" /><figcaption>Oligodendrocytes derived from a multiple sclerosis patient. Image credit: Maria Sapar, PhD</figcaption></figure><h4><strong>Predicting passage time</strong></h4><p>Using a training set from NYSCF’s data, our team of volunteers set forth investigating three different modeling approaches:</p><ol><li>A naïve logic-based approach to set a baseline</li><li>A survival model</li><li>A Bayesian model</li></ol><p>The baseline model was simple. Once a well hit a defined confluence, the ideal passage time would fall within a range of hours later. Not only did this model help us set a baseline, but it also helped us assess if the complexity of the following models ultimately added value.</p><p>Next up was the survival model, which is typically used in the medical field. This methodology is generally used to assess the likely amount of time to an event. Under the surface, it’s essentially producing the probability of the event happening over time. We had to apply this twice: once for the start of the optimal transfer window and once for the close of the optimal transfer window. The mechanics and complexity of this approach allow for fine-tuning to reach a precision and recall ideal for its application, with its tradeoff being more demanding compute needs whenever it needs to be retrained.</p><p>Finally, the Bayesian model is an approach that allows for real-time adjustments in response to new data. Using the fundamental concept of cell growth rate, the Bayesian approach essentially predicts the confluence level at every point in time, given all the confluence levels captured thus far. The benefit of this approach is that it quickly adapts to new observations after data capture errors, which can be an advantage in real-time applications.</p><h4><strong>Comparing performance</strong></h4><p>When it came to cross-model comparisons, we chose to assess ultimate performance using each model’s f-score, the<a href="https://en.wikipedia.org/wiki/Harmonic_mean"> harmonic mean</a> (a numerical average typically used when finding the average of rates) of the precision and recall of a model. In this specific case, a high precision meant that we reduced the chances a well would be transferred too early (not enough cells), and a high recall meant that we reduced the chances a well would be transferred too late (it will have differentiated). F-scores range from 0 to 1 (1 being perfect precision and recall).</p><p>The Bayesian and Survival models had strikingly similar f-scores, with slight variation in the strength of precision vs. recall. For something so straightforward, the baseline model performed surprisingly well on precision, but its low recall meant that a large number of cell lines would likely remain in wells for too long. In the end, the added complexity of the other two approaches would indeed be worth the investment to ensure higher quality samples.</p><h4><strong>Putting it into practice</strong></h4><p>NYSCF’s research team was eager to test both models live on their system to make the ultimate decision between the Bayesian and Survival models. With both codebases in hand, NYSCF is currently implementing both approaches, first testing the models on real-time data and then conducting comparative analyses. In parallel, NYSCF is simultaneously capturing feedback from researchers on whether they agree with the model’s call to begin developing a novel ground-truth dataset. We look forward to putting our heads back together with NYSCF to assess the performance of both approaches, as well as their experience managing the pipeline.</p><h4>Part II t<strong>easer</strong></h4><p>How exactly do the technicians review the state of iPSC growth in some of these experiments with the TGSCA™? The NYSCF team not only built their own proprietary robotic system, but also layered on a custom laboratory information management system (LIMS) that has allowed researchers to collect and interact with data and images through custom desktop and web-based applications.</p><p>Look out for our next blog in this series to learn about a tool we designed to interact with data generated by NYSCF’s <a href="https://nyscf.org/open-source/monoqlo/">Monoqlo℠</a> system, and hear how our team of volunteer engineers collaborated with NYSCF on improvements to their software solution so they can seamlessly adapt to their expanding resources.</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=b1f1ef9ab169" width="1" height="1" alt=""><hr><p><a href="https://medium.com/dataclinic/applying-data-science-to-optimize-stem-cell-production-b1f1ef9ab169">Applying Data Science to Optimize Stem Cell Production</a> was originally published in <a href="https://medium.com/dataclinic">Data Clinic</a> on Medium, where people are continuing the conversation by highlighting and responding to this story.</p>]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Using data to expand equitable arts programming in Nashville]]></title>
            <link>https://medium.com/dataclinic/using-data-to-expand-equitable-arts-programming-in-nashville-34a1e514f37?source=rss-bc81171ecd11------2</link>
            <guid isPermaLink="false">https://medium.com/p/34a1e514f37</guid>
            <category><![CDATA[government]]></category>
            <category><![CDATA[data-for-good]]></category>
            <category><![CDATA[open-data]]></category>
            <category><![CDATA[projects]]></category>
            <category><![CDATA[arts-and-culture]]></category>
            <dc:creator><![CDATA[Data Clinic]]></dc:creator>
            <pubDate>Thu, 28 Oct 2021 17:26:36 GMT</pubDate>
            <atom:updated>2021-10-28T17:30:14.533Z</atom:updated>
            <content:encoded><![CDATA[<h3>Using Data to Expand Equitable Arts Programming in Nashville</h3><h4>In partnership with Metro Nashville Arts, we analyzed data on various arts initiatives in Nashville to provide insights on widening their reach equitably</h4><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*guQNQnb-Z1SPprXac6uvww.jpeg" /><figcaption><em>Ghost Ballet for the East Bank Machineworks (</em>Artist: Alice Aycock Photographer: Gary Layda)</figcaption></figure><p>Widespread and equitable access to arts and culture is an important aspect of any city’s community planning. Art programming can provide meaningful opportunities for community engagement, creativity, and togetherness — something we’ve all learned to value more than ever during the Covid-19 pandemic. Therefore, ensuring equitable access to art and culture is an important priority for many arts organizations, including the Metro Nashville Art Commission, or “Metro Arts.” Metro Arts is the office of Arts and Culture for Nashville and Davidson County in Tennessee, and it strives to create a vibrant and equitable community through arts by funding nonprofit arts and cultural organizations, public art, artists and youth programs.</p><p>Each year, Metro Arts has to decide how to allocate its limited funds among a growing number of organizations. While Metro Arts’ funding has remained relatively flat over the last decade, the number of organizations applying for support has increased. This makes the decision-making process as to how much to give each organization more challenging. Metro Arts traditionally uses a holistic, qualitative review of the various organizations to determine funding allocations. While Metro Arts collects various data about its funded organizations and their projects and participants, it has historically faced many challenges to using that data effectively in its processes. These challenges include inconsistent data collection, limited staff resources and experience with data analysis. Metro Arts’ goal is to ensure that all Nashvillians have equitable access to a creative life, with a particular emphasis on ensuring that Black, Indigenous, People of Color (BIPOC) communities and communities with higher rates of poverty have the same access as everyone else.</p><p>We had the opportunity to help the organization address some of the knowledge gaps and challenges it’s faced around data analysis. We’ve also been able to apply a quantitative lens to the work Metro Arts has been doing to allocate its resources equitably.</p><p>For each category of Metro Arts’ programming, we set out to answer two questions: (1) Can we estimate the reach of Metro Arts’ funded initiatives based on currently available data? and (2) can we provide Metro Arts with data-driven insights on funding allocations going forward? We analyzed the data provided by Metro Arts holistically and supplemented it with various publicly available data sets. We also used the FY 2019–2020 data to provide more targeted insights for Metro Art’s grant applications review this year.</p><h3>Public Art</h3><p>In order to evaluate the current reach of public artworks and help identify public spaces in high poverty and BIPOC communities for new public art, we analyzed the locations of public art provided by Metro Arts (1989–2019). We also examined data from the US Census Bureau to better understand the demographic makeup of the communities in the vicinity of public art and used <a href="https://www.walkscore.com/professional/api.php">Walk Score</a> data to quantify potential pedestrian access to these installations.</p><p>We discovered that about 50% of council districts in Nashville (out of 34) have no public artworks, which provides an opportunity for Metro Arts to expand its reach. Some Council Districts are primarily residential, since Nashville is a city/county government which includes urban, suburban and rural areas, so one possible set of potential locations for new artworks are Nashville Metro Parks, the data for which is made available through <a href="https://data.nashville.gov/Parks/Metro-Parks-Boundaries-GIS-/728b-6yiv">metro park boundaries dataset </a>on the Nashville Open Data Portal. The maps below demonstrate where public artworks are located (dots), the locations of parks from Metro Park boundaries (orange regions), and census information color-coded to reflect the percentage of BIPOC population and the percentage of population living below the poverty level in each tract. From these maps, Metro Arts can glean insights about how equitably public art is distributed across different communities, in particular those with a high proportion of BIPOC and high poverty residents (i.e., the North-West and South-East regions of the city). These communities tend to have low exposure to permanent artworks and are considered “key regions” in Metro Art’s effort to ensure equitable access to public art.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/822/0*7_BKWYYf93G3j0d3" /><figcaption>Demographic distribution in Nashville with locations of public artworks (dots) and Metro parks (orange regions)</figcaption></figure><p>To help Metro Arts identify promising candidates for public artworks in prioritized regions of the city, we leveraged the Walk Score of each region. A Walk Score, ranging from 0 to 100, quantifies how “walkable” a neighborhood is by assessing various factors such as nearby amenities, accessibility to public transport, walking routes, and population density. It can serve as a proxy for accessibility of a location, indicating that there’s a higher likelihood that people would visit public art in an area with a higher Walk Score. The map below demonstrates the average Walk Score for each census tract in Nashville. Not surprisingly, the highest average Walk Scores are in the downtown areas of Nashville (80–100), while parts in the South-East have relatively high scores as well (above 50). Because most public art installations are in the downtown area of Nashville, they are located in regions with a high Walk Score. Since some of the factors that are considered in Walk Scores are also commonly associated with more expensive neighborhoods in cities, we assessed potential bias in the Walk Score (i.e., is a higher Walk Score correlated with higher income and/or lower BIPOC proportions in an area), but did not find significant evidence of these associations. Therefore, each region’s Walk Score can be a helpful metric for Metro Arts to consider going forward in terms of selecting easily accessible locations for public art. Metro Arts particularly appreciated this insight, as its assumption was that high Walk Score neighborhoods are limited to predominantly less diverse neighborhoods. “There are plenty of high Walk Score BIPOC neighborhoods we can consider for future public art,” said Janine Christiano, Strategic Funding and Initiatives Manager at Metro Arts.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/672/0*PLve5A46bhWWGfb9" /><figcaption>Average WalkScore across Nashville (lighter colors indicate higher score)</figcaption></figure><p>We provided different metrics including average Walk Score, percentage of BIPOC and low-income residents, nearby public art, and nearby parks for all of the parks available in the Nashville metro park boundaries database. We then highlighted specific parks that could be of interest to Metro Arts, due to their proximity to neighborhoods with underserved populations and fewer current nearby installations (such as Ted Rhodes Park, White Creek Park, and Grassmere Park). We will also provide Metro Arts with code to generate these types of metrics for any new location going forward. These metrics, when used in conjunction with more qualitative information, can help Metro Arts to determine potential future locations for public art installations that expand access to underserved communities.</p><h3>Funded Organizations</h3><p>Each year, Metro Arts provides funding for an increasing number of organizations (over 60 in 2018) that organize art and culture projects in hundreds of locations including schools, parks, and museums. Data about the funded organizations and their project locations from 2015–2017 and 2019–2020 includes a self-reported number of participants and event occurrences at each location. We combined this with information from the census to help analyze these organizations’ reach to BIPOC and low-income communities and to provide insights into potential locations for increasing equitable program reach.</p><p>As discussed above in the context of public art, we identified certain “key regions,” highlighting areas that have a high number of BIPOC and people living in poverty, but that do not have a high concentration of permanent public artworks (i.e., the northwest and southeast parts of Nashville). The maps below show all project locations in red and the size of each population category for each census tract in teal circles.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1000/0*Q0QmgU9-bYEhF9dP" /><figcaption>Distribution of population across Nashville (red dots: program locations; teal circles: population)</figcaption></figure><p>We faced a number of challenges in the process of understanding an organization’s reach. First, we don’t actually have data on who is accessing these projects — so quantifying their exposure requires a number of assumptions and proxies. Since we do have data on the locations of the initiatives, we were able to use data from the census to figure out the demographic makeup in the vicinity of these locations. First we drew a circle around each project using a radius of 1 mile to represent the participating population, and from there we estimated the potential reach for different organizations based on the locations they operate in.</p><p>Of course, it can be hard to compare different types of funded projects and organizations on the same scale because their catchment areas (i.e., the geographic areas they serve) can be very different. For example, an organization like Nashville Symphony is expected to reach many people around the city outside of its immediate radius for Symphony productions, since many will travel to attend these types of events. For smaller, more local organizations like the Porch Writers’ Collective, we assumed that people within a 1 mile radius would be more likely to attend than those living further away. Therefore, when conducting the analysis on the reach of funded projects, we excluded certain project locations with a large number of participants, since estimating participation based on vicinity is likely not valid.</p><p>Reach was measured across several dimensions, including percentage of BIPOC population and people living in poverty in the vicinity of each program location, what types of locations the activities typically take place in, whether the organization’s program locations are in the key regions described above, and the number of participants and events reported by organizations.</p><p>There is a significant variance in the percentage of BIPOC and percentage of people living in poverty in the vicinity of each project location. The plot below compares the percentage of overall BIPOC population each organization could reach versus the average percentage of the BIPOC population in the vicinity. The dot size is scaled by the number of locations each organization operates in. This data can support efforts to focus funding on organizations that work in areas with a high proportion of the target demographics while simultaneously reaching a significant portion of the population, as well. The arrows show the direction in which these dots could move in the future to increase programming to more diverse locations (by targeting organizations that have a high overall reach across Nashville and also have a large BIPOC population in the vicinity) or that could widen local reach (by looking at organizations with relatively lower overall reach that typically work in high minority neighborhoods).</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/982/0*FdkweZMmXbqAY204" /><figcaption>Visualizing the local and overall BIPOC population with potential to reach for all organizations</figcaption></figure><p>We also used data from the census to help identify access trends across different location types, with certain locations such as public schools, organizations receiving the <a href="https://www.metroartsnashville.com/thrive">Thrive grant</a>, libraries, and arts and culture facilities reaching a larger percentage of the target communities as compared to other location types. Funding activities in these locations can potentially help Metro Arts increase arts access to underserved communities.</p><h3>School Programs</h3><p>In order to evaluate the reach and diversity of schools served by organizations that receive Metro Arts’ grants, data on organization-school partnerships, including the estimated number of students reached through school programming and school locations (2015–2017; 2018–2020) was supplemented with Metro Nashville Public School (MNPS) <a href="https://mnps.org/about/communications/opendata">enrollment data</a>.</p><p>On a high level, organizations working with schools typically engage with about 5 to 10 schools, and each school generally receives support from 1 or 2 organizations. The majority of the partnerships are with MNPS, which also have a higher proportion of BIPOC students than the general population in Nashville under 18. Given Metro Arts’ high engagement with MNPS, as well as a lack of data on non-public schools, we focused the analysis on public rather than private schools.</p><p>As with public artworks and funded projects, we conducted analysis across a number of different metrics to measure potential reach of each organization’s work with schools, including the number of public schools working with the organization, the overall proportion of the student population potentially reached by programming, and detailed statistics broken down by key characteristics (i.e., by race/ethnicity, students with limited English proficiency, students with disabilities, and economically disadvantaged students). In particular, we provided information about the percentage of the overall MNPS student population for each socio-demographic group that each organization can potentially reach (e.g., of all economically disadvantaged students in MNPS, how many attend schools working with a particular organization).</p><p>Metro Arts can see how its grantees are doing in terms of reaching schools with higher populations of its target demographics. The chart below demonstrates the total students per school broken down by demographic categories (in orange), compared to the students in those same categories reached by Metro Art grantees (in teal). Overall, Metro Art grantees are serving different student populations on a level that’s close to the city average. They’re serving a relatively high number of schools with greater Hispanic/LatinX student populations, and a more narrow range of schools with Black students.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1000/0*f7klNkK5edRclrhY" /><figcaption>Comparing the demographics across all Public schools and those that work with grantees</figcaption></figure><p>We compared the percentage of low-income and BIPOC students each organization can potentially reach versus the average percentage of those demographics in schools each organization works with. This comparison helped us identify organizations that work in schools with higher populations of the target demographics while simultaneously reaching a significant proportion of the overall student population of each demographic as well. The scatter plots below demonstrate this comparison and the dots are scaled to represent the number of public schools each organization works with.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1000/0*hMIj68AGAWSY9e7a" /><figcaption>Average school-level and overall student population distribution with potential to reach for each organization</figcaption></figure><p>We also helped identify schools not currently reached by funded organizations that would help expand access to Metro Arts’ target demographics because they have both a large school population and a high proportion of target demographics. A deeper analysis on organizations’ reach to schools over time would be needed to prioritize these schools, since organizations have full discretion to select the schools they work with. Organizations that have expanded their reach in the past may be more receptive to expansion in the future, and additional funding may or may not have an impact on an organization’s desire to expand reach. Given its relationship with grantees, Metro Arts can supplement its understanding of these dynamics with the results from our analysis to inform longer term decisions on expanded reach in schools.</p><h3>Key takeaways</h3><p>Overall, funded organizations’ focus on public schools skews toward Metro Arts’ target demographics, and grantees already have a significant reach within MNPS. To further equitable engagement to arts programming in schools, Metro Arts can work with organizations to focus on schools serving BIPOC students and those that are geographically isolated from other schools with funded programs.</p><p>In addition to the insights into how to expand equitable access to arts programming, this project helped to highlight the importance of data quality and consistency. Metro Arts indicated that an audit of their data collection methods and current data would have been very helpful from the start of the project. “We discovered during the process how much of our data needed clean-up to be usable and what we eventually needed to update,” said Christiano.</p><p>Metro Arts is excited to use the insights from this project in both the public artwork selection process and annual grants allocation process. “We now have a clear idea of what organizations have been most successful in reaching high-poverty and BIPOC communities, so we can begin to dig deeper and look at what exactly these organizations do well that contributes to this impact, and help other organizations grow in this way. We also know what locations will be most impactful and most in line with our strategic goals,” Christiano indicated.</p><p><em>A special thanks to Metro Arts for their collaboration and to Lilia Stantcheva for writing this blog.</em></p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=34a1e514f37" width="1" height="1" alt=""><hr><p><a href="https://medium.com/dataclinic/using-data-to-expand-equitable-arts-programming-in-nashville-34a1e514f37">Using data to expand equitable arts programming in Nashville</a> was originally published in <a href="https://medium.com/dataclinic">Data Clinic</a> on Medium, where people are continuing the conversation by highlighting and responding to this story.</p>]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Pro Bono Week 2021]]></title>
            <link>https://medium.com/dataclinic/pro-bono-week-2021-7a830491f01a?source=rss-bc81171ecd11------2</link>
            <guid isPermaLink="false">https://medium.com/p/7a830491f01a</guid>
            <category><![CDATA[nonprofit]]></category>
            <category><![CDATA[social-impact]]></category>
            <category><![CDATA[data-clinic]]></category>
            <category><![CDATA[data-science]]></category>
            <category><![CDATA[data]]></category>
            <dc:creator><![CDATA[Data Clinic]]></dc:creator>
            <pubDate>Mon, 25 Oct 2021 14:00:49 GMT</pubDate>
            <atom:updated>2021-10-25T14:00:49.447Z</atom:updated>
            <content:encoded><![CDATA[<h4>Reflecting on 7+ years of learning and growing in our pro bono collaborations thanks to the dedication and generosity of our partners</h4><figure><img alt="An illustrated scene with 2 individuals talking and shaking hands, 2 working at computers, and 2 working on a project board. Next to this is the hashtag ProBonoWeek and in the bottom right hand is the logo for Data Clinic" src="https://cdn-images-1.medium.com/max/800/1*XD1fpkh0oQcZMj7jqAAn_w.png" /></figure><p>The American Bar Association started the <a href="https://www.probono.net/celebrateprobono/">National Celebration of Pro Bono</a> in 2009 to address the increased need for pro bono legal services during the economic crisis. Other industries, whose pro bono initiatives have similarly grown in scale and demand, joined the celebration and since 2013, <a href="https://globalprobono.org/events/week/">Global Pro Bono Week</a> has been a key opportunity to raise awareness about pro bono work across sectors.</p><p>This Pro Bono Week, <a href="https://dataclinic.twosigma.com/">Data Clinic</a> would like to take a moment to reflect back on our first 7+ years as Two Sigma’s pro bono data- and tech-for-good initiative, and give thanks to the hundreds of mission-driven partners who have entrusted us with their data and tech needs and committed to meaningful collaborations and conversations, all the way from early introductory chats to engaging in official projects. Together, we have worked toward purposeful impact through the skills and experience that make all our organizations unique.</p><p>We would be remiss if we didn’t call out in particular the substantial impact our partners have had on all of our volunteers and all of us at Data Clinic. In every partnership, we receive and learn every bit as much as we give in technical support and capacity building. Our partners go the extra mile to share their wealth of knowledge on the social issues they tackle day-in and day-out, their nuanced understanding of the community members they seek to support, and their thoughtful approach to their programming, services, and operations.</p><figure><img alt="Two people sharing information with each other" src="https://cdn-images-1.medium.com/max/1024/1*sr6X4OjSyoKCsaLRezC_tQ.png" /></figure><p>To share just a few examples of this generosity of spirit, time, and knowledge:</p><ul><li>We partnered with the <a href="https://nysci.org/">New York Hall of Science</a> (NYSCI) to analyze data from their <a href="https://classic.nysci.org/experiencenysci/exhibits/connected-worlds/">Connected Worlds</a> exhibit in order to provide <a href="https://www.twosigma.com/articles/data-clinic-nysci-investigating-visitor-behavior-at-an-interactive-museum-exhibit/">actionable insights to guide visitors on the impact of their actions on the health of the ecosystems</a>. NYSCI’s took the time to walk us through the exhibit in person so we could truly understand the immensity and richness of the experience they designed, and the impact this analysis could have on visitors.</li><li>We partnered with the <a href="https://nyscf.org/">New York Stem Cell Foundation</a> (NYSCF) to analyze data on their Global Stem Cell Array in order to help <a href="https://nyscf.org/resources/artificial-intelligence-meets-disease-research-how-a-new-partnership-is-streamlining-nyscfs-science/">optimize the process of creating induced pluripotent stem cells</a> that are crucial to their research on disease treatments. NYSCF brought us to their lab and walked us through the extraordinary machinery and automated process they developed so we could incorporate a nuanced appreciation of their groundbreaking work into our collaboration.</li><li>We had the honor of working with <a href="https://www.vera.org/">Vera Institute of Justice</a> on two different and fascinating projects: one analyzing the <a href="https://www.twosigma.com/articles/explaining-the-rurality-of-americas-jails-data-clinic-vera-institute-of-justice/">disparity of jail incarceration rates between rural and urban areas</a>, and one <a href="https://medium.com/dataclinic/announcing-a-consolidated-dataset-of-911-calls-for-five-us-cities-part-1-4320a1a31a88?source=collection_home---4------0-----------------------">cleaning, compiling, and analyzing open 911 data</a> across several cities. Vera put a lot of time into collaborating with us across these two projects, ensuring that the insights could lead to valuable actions and research in their advocacy for a fair criminal justice system. In kind, our awareness of the interplay of issues in criminal justice has grown immensely.</li></ul><p>Thanks to experiences like these with our partners, our grasp of the complexity of social issues and the challenges of operating mission-driven organizations never ceases to grow, and in kind, our pro bono data and tech support will never cease to evolve. We look forward to countless years ahead of building thoughtful and innovative pro bono collaborations to respond to our communities’ social impact needs.</p><p>Interested in partnering with us? <a href="https://airtable.com/shrwBoVEJ6nOuKUFh">Fill out our contact form</a>!</p><figure><img alt="One person sits at a desk, another leans against a stool and they’re sharing and discussing documents with each other" src="https://cdn-images-1.medium.com/max/1024/1*KqmVa_SttOtZ_0UwkqZWLg.png" /></figure><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=7a830491f01a" width="1" height="1" alt=""><hr><p><a href="https://medium.com/dataclinic/pro-bono-week-2021-7a830491f01a">Pro Bono Week 2021</a> was originally published in <a href="https://medium.com/dataclinic">Data Clinic</a> on Medium, where people are continuing the conversation by highlighting and responding to this story.</p>]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Good with Numbers]]></title>
            <link>https://medium.com/dataclinic/good-with-numbers-fac382fc3725?source=rss-bc81171ecd11------2</link>
            <guid isPermaLink="false">https://medium.com/p/fac382fc3725</guid>
            <category><![CDATA[tech-for-good]]></category>
            <category><![CDATA[data-clinic]]></category>
            <category><![CDATA[nonprofit]]></category>
            <category><![CDATA[data]]></category>
            <category><![CDATA[data-science]]></category>
            <dc:creator><![CDATA[Data Clinic]]></dc:creator>
            <pubDate>Tue, 03 Aug 2021 17:43:51 GMT</pubDate>
            <atom:updated>2021-08-03T17:43:51.206Z</atom:updated>
            <content:encoded><![CDATA[<h4>Introducing Data Clinic’s free quarterly workshop series for nonprofits, which aims to help<em> make data work for their missions and their communities</em></h4><figure><img alt="" src="https://cdn-images-1.medium.com/max/960/1*t_ihZZoH0Evn26FnP1gD0g.png" /></figure><p>In the new Good with Numbers workshop series, join Data Clinic in a small-group format to learn actionable tips on how to build data strategies and how to make data more valuable, both to your mission-driven organization and the communities you serve. In each workshop, we’ll cover a core concept of responsible and strategic data use, then split into breakout rooms guided by Data Clinic staff to ensure that every attendee confidently walks away with new learnings.</p><h3>Join the first workshop on August 17th, 2021</h3><p>In our first virtual workshop Tuesday, August 17, 2021<strong> </strong>from 12:30–1:30pm ET, we will focus on <a href="https://www.eventbrite.com/e/good-with-numbers-5-tips-to-narrow-in-on-a-strong-data-project-scope-tickets-165164143399?aff=ebdsoporgprofile"><strong>5 tips to narrow in on a strong data project scope</strong></a>.</p><p>It’s important to have a strong research question to drive any data analysis your organization engages in. A groundwork built on intention and focus maximizes the chances of success and paves the way for responsible data use, both for solo and collaborative projects.</p><p>These tips aren’t just for those early in their data journey. At Data Clinic, we use these tips over and over again in all our project scoping conversations, even with those that have full-time data and research staff.</p><p>Attendees will walk away with at least one research question to drive their next data project forward, and inspiration from fellow nonprofits’ data and tech-related goals.</p><h3>Who should attend?</h3><p>These workshops are reserved for employees of nonprofits:</p><ul><li>CEOs</li><li>Data analysts</li><li>Executive directors</li><li>Staff members</li><li>Program officers</li><li>Research staff</li></ul><h3>RSVP</h3><p>Space is limited to 20 nonprofits. <a href="https://www.eventbrite.com/e/good-with-numbers-5-tips-to-narrow-in-on-a-strong-data-project-scope-tickets-165164143399?aff=ebdsoporgprofile">RSVP here to reserve your spot in the August 17th workshop</a>.</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=fac382fc3725" width="1" height="1" alt=""><hr><p><a href="https://medium.com/dataclinic/good-with-numbers-fac382fc3725">Good with Numbers</a> was originally published in <a href="https://medium.com/dataclinic">Data Clinic</a> on Medium, where people are continuing the conversation by highlighting and responding to this story.</p>]]></content:encoded>
        </item>
    </channel>
</rss>