<?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[DSSG Berlin Blog - Medium]]></title>
        <description><![CDATA[Geschichten rund um http://dssg-berlin.org - Medium]]></description>
        <link>https://medium.com/dssg-berlin-blog?source=rss----7d22a7d5aea5---4</link>
        <image>
            <url>https://cdn-images-1.medium.com/proxy/1*TGH72Nnw24QL3iV9IOm4VA.png</url>
            <title>DSSG Berlin Blog - Medium</title>
            <link>https://medium.com/dssg-berlin-blog?source=rss----7d22a7d5aea5---4</link>
        </image>
        <generator>Medium</generator>
        <lastBuildDate>Tue, 17 Nov 2026 06:53:01 GMT</lastBuildDate>
        <atom:link href="https://medium.com/feed/dssg-berlin-blog" rel="self" type="application/rss+xml"/>
        <webMaster><![CDATA[yourfriends@medium.com]]></webMaster>
        <atom:link href="http://medium.superfeedr.com/" rel="hub"/>
        <item>
            <title><![CDATA[DSSG Datathon 2023: One fun weekend of coding and social good]]></title>
            <link>https://medium.com/dssg-berlin-blog/dssg-datathon-2023-one-fun-weekend-of-coding-and-social-good-652a6296ab8c?source=rss----7d22a7d5aea5---4</link>
            <guid isPermaLink="false">https://medium.com/p/652a6296ab8c</guid>
            <dc:creator><![CDATA[Vadim Voskresenskii]]></dc:creator>
            <pubDate>Thu, 03 Aug 2023 18:12:18 GMT</pubDate>
            <atom:updated>2023-08-03T18:12:18.380Z</atom:updated>
            <content:encoded><![CDATA[<p>One of the essential activities organised by DSSG Berlin are datathons. For these events, we invite data analysts and data scientists to spend a whole weekend helping non-profit organisations with their data-related challenges. This year, we organised the datathon in an online format on the weekend of March 24–26. The online format allowed people from different parts of the world to take part in the event. Finally, 25 data enthusiasts joined us this weekend. While almost half of these volunteers live in Europe, we also had people from Asia, Africa, and North and South America. We had a balanced gender split amongst the participants and a great mix of different experience levels.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/817/1*NLBhD6ENC-r3eCh_FgTQ_Q.jpeg" /><figcaption>Distribution of participant by geographic regions</figcaption></figure><p>One of the most important lessons we learned from the previous editions of the datathon is that datasets provided by NGOs should be properly researched and preprocessed before the actual event. The format of the datathon (which is limited to one weekend) does not give volunteers enough time to create a well-developed design for analysis and to clean and preprocess the data. Hence, it was very important for us to spend enough time before the event on brainstorming how the analytics goals of NGOs can be achieved and to get acquainted with data to make the work of volunteers during the datathon more efficient and fruitful for NGOs. As in the previous datathons, we therefore invited experienced data volunteers from our network, who were eager to take the role of data ambassadors and support the participants during the event.</p><p>The first project came from the organisation <a href="https://welttierschutz.org/">WTG e.V. | Welttierschutzgesellschaft</a>, which fights for the improvement of animals’ life conditions in developing countries. The activity of the organisation financially depends on donations from their supporters. The ojective for this NGO was to get a detailed analysis of the dynamics of donors’ behavior, to better understand which projects attain financial support, and from which parts of Germany they get the biggest contributions. For solving these challenges, the volunteers employed methods of exploratory analysis and predictive modeling. To understand the origins of donations, the participants produced detailed maps showing how contributions vary between federal states in Germany.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*fxJNyXjNEKVMzJR7dUsigA.png" /><figcaption>Map is showing how amount of donations varies by regions of Germany</figcaption></figure><p>The participants also found differences in financial support between genders. According to the analysis, women give higher total donation amounts overall, and they are particularly much more interested than men in supporting projects connected with climate crisis issues.</p><p>Another project was proposed by <a href="https://www.wirfuervielfalt.de/">Wir für Vielfalt</a>; the organisation focuses on facilitation of diversity in learning environments. In the framework of the datathon, they wanted to get a better understanding of how their audiences use their website and which pages (or topics) are more interesting. Based on the data provided by NGO, the team of volunteers calculated a “Bounce rate” metric, which represents a proportion of visitors leaving a website without taking any action. The volunteers also showed how the average bounce rate varies between different categories on the website. Knowing these numbers, the NGO can better understand which directions of their work are more interesting for audiences and which parts of their work need additional development. Moreover, the volunteers prepared a very detailed presentation for the NGO, showing how much time in average visitors spend on the website, how many pages they open, and what are the most interesting themes for visitors.</p><p>An equally interesting and important part of the analysis was to explore from which external webpages people come to the website of the NGO. This type of analysis is very helpful for the organisation, as it gives a nice overview of their audiences’ interests and can improve the efficiency of targeting campaigns to attain more subscribers and visitors.</p><p>The third non-profit organisation taking part in the datathon was <a href="https://www.harambee.co.za/">Harambee Youth Employment Accelerator</a>. The main goal of Harambee is to decrease the level of unemployment among youth in South Africa. Harambee works on the improvement of a matching process between young people searching for job opportunities and the job positions existing on the market. To improve this matching, Harambee asks candidates to record short messages in English to estimate their level of English proficiency. For this project, Harambee had a collection of these short recordings, and half of them have already been classified by professional graders based on the CEFR scale (A1, A2, etc.). The task for volunteers was to train a machine learning model that could predict the level of English based on this pre-classified collection. Besides that, Harambee wanted the volunteers to give them an overview of the quality of existing recordings and to come up with a proposal on how to improve the collection of audio data in the future.</p><p>The volunteer team tried two approaches to this challenge. In the first one, they transcribed the audio data into texts and applied the NLP algorithm ROBERTA for the classification. For making a classification, they enriched data by adding the information from the CEFR dataset, which was in public use. This approach gave an accuracy of 0.68, which is quite a good score for the first iteration of analysis taking into account the complexity of the data. In the second approach, the team extracted text-independent acoustic features of the recordings and employed signal processing to clean signals. The next step for the team will be the implementation of complex neural nets to predict scores of recordings based on their acoustic features.</p><p>It is already the sixth datathon that DSSG Berlin organised, but we are still impressed by the fact that so many people are ready to spend their free time working as a volunteer on quite complex projects. And it is always very exciting to see how many valuable outcomes our volunteers can produce in such a short period of time. A long and detailed discussion of the results between volunteers and NGOs during the presentations on the final day of the datathon shows the importance of such events for both sides and motivates us to organise these events. We are very grateful to all NGOs, volunteers, and data ambassadors, who took part in this event, and we are looking forward to the next edition of the datathon!</p><p>Vadim Voskresenskii &amp; Lisa Zäuner (DSSG core team)</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=652a6296ab8c" width="1" height="1" alt=""><hr><p><a href="https://medium.com/dssg-berlin-blog/dssg-datathon-2023-one-fun-weekend-of-coding-and-social-good-652a6296ab8c">DSSG Datathon 2023: One fun weekend of coding and social good</a> was originally published in <a href="https://medium.com/dssg-berlin-blog">DSSG Berlin Blog</a> on Medium, where people are continuing the conversation by highlighting and responding to this story.</p>]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[DSSG Datathon 2021: Organizing an online Datathon]]></title>
            <link>https://medium.com/dssg-berlin-blog/dssg-datathon-2021-organizing-datathon-in-online-format-8725ed153272?source=rss----7d22a7d5aea5---4</link>
            <guid isPermaLink="false">https://medium.com/p/8725ed153272</guid>
            <dc:creator><![CDATA[Vadim Voskresenskii]]></dc:creator>
            <pubDate>Thu, 17 Mar 2022 20:26:50 GMT</pubDate>
            <atom:updated>2022-03-18T09:02:07.889Z</atom:updated>
            <content:encoded><![CDATA[<p><em>What is a datathon?</em></p><p>Datathons are crucial activities that DSSG Berlin organizes almost every year. A datathon of DSSG is a short (usually not more than one weekend) and very intensive event at which volunteering data analysts and data scientists work in small groups on data-related challenges coming from German non-profit organizations. The aim is not to prepare the final solution for a problem but rather to outline the main directions in which the project can be developed and to investigate the issue from different perspectives. Therefore, it is important to have participants who possess various backgrounds and skill sets. Another essential part of datathons are our data ambassadors. These are data analysts who prepare, clean, and structure the relevant data from non-profit organizations beforehand to make potential analyses on the day of the datathon feasible.</p><p><em>Our remote datathon 2021</em></p><p>Before the pandemic in 2020, we organized datathons in real-life format. However, new restrictions related to Covid-19 and the overall desire of people to avoid big gatherings posed a new challenge to us. How to organize a datathon in a Covid era? We decided to create an online event. Zoom was used for project and final presentations. Moreover, participants used breakout rooms in Zoom to discuss and organize the process of the data analysis. In Slack channels, volunteers discussed problems and shared initial results and drafts of presentations.</p><p>The datathon took place on the weekend 19–21 November 2021. On Friday, the participants were introduced to the challenges and had a chance to socialize and think of potential solutions. On Saturday, volunteers worked on the projects conducting various analyses and on Sunday, the final results were presented to the non-profit organizations. A lively discussion about the results and potential implications showed the value and impact of our volunteers’ work. In addition to the main program, we had presentations from our sponsors, ResearchGate and Kineo.ai, and a talk about participative democracy and AI from Luke Jordan (MIT). To make this event more similar to real/offline events with regular coffee breaks and socialization, we ordered food for all our participants to jointly have a remote dinner in a customizable calling space Gather. Furthermore, to ensure that our volunteers stay motivated and keep their energy levels up, we provided goodie bags for everyone that included some sweets and treats, such as energy bars, chocolate, and tea.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/283/1*9W0NitHAv1bF9RW5StqkRQ.jpeg" /></figure><figure><img alt="" src="https://cdn-images-1.medium.com/max/283/1*BrKTWtyANBe16HkpQ9Aa1w.jpeg" /><figcaption>Left: Contains of a goodie bag; Right: Remote dinner in Gather</figcaption></figure><p>Finally, with more than 30 active participants and due to the digital format, we were able to create an international event with people from all over Europe. Our participants came from industry and academia and had various experiences with data analytics, thus allowing a very diverse project team formation. They worked on challenges offered by three non-profit organizations: <em>ADFC </em>(the Allgemeiner Deutscher Fahrrad Club), <em>DRK </em>(the German Red Cross), and <em>Bezirksamt Friedrichshain-Kreuzberg</em>.</p><p><em>Challenges and results</em></p><p>The <a href="https://www.adfc.de/"><strong>ADFC</strong></a><strong> </strong>acts as Germany’s cycling lobby and supports more than 200,000 members with a diverse range of services and assistance, such as roadside assistance or liability and legal costs insurance. The ADFC promotes the development of a better cycling infrastructure in German cities. To support their demands and to convince local governments and politicians, ADFC requires evidence that people actually switch from motorized vehicles to bicycles and that cycle lanes are a beneficial investment to address our climate crisis. Volunteers who signed up to help the ADFC made use of data from bike traffic counting stations and combined it with weather and Covid-19 data to analyze and substantiate ADFC’s arguments for further expansion and improvement of the cycling infrastructure.</p><p>Multiple visualizations for various German regions were created and handed over together with conclusions and recommendations drawn from the data analysis.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/858/1*909sXuEzve4C_JxB5d8ydw.png" /><figcaption>One of the vizualizations made by participants working on the ADFC project</figcaption></figure><p>Together with more than three million members, the<a href="https://www.drk.de/en/"> <strong>DRK</strong></a><strong> </strong>is one of the biggest welfare organizations in Germany and runs multiple hospitals and nursing homes. These are also affected by the shortage of care work specialists that was already alarming and now becomes more and more evident during the Covid-19 crisis. To support the DRK recruiting, volunteers used job portal data to examine job postings regarding their effectiveness. To be precise, volunteers analyzed different aspects of job descriptions and how they influence the number of applications. Therefore, website traffic data was combined with the job description, and different NLP (natural language processing) techniques were used to investigate the impact of different aspects. One finding, for example,was that the proportion of applications to apprenticeship job postings is 4 to 1. The volunteers thus concluded that there is an interest of young people to work in the social sector but the number of apprenticeships might not properly accommodate this interest. These very interesting results were also presented at the <em>Future of Care</em> <em>Event </em>after our Datathon. This was an internal meeting at the DRK focusing on issues related to care work. Thereby, the volunteers were able to support and advise the DRK recruiting on how job postings should be improved.</p><p><a href="https://www.berlin.de/ba-friedrichshain-kreuzberg/"><strong>Bezirksamt Friedrichshain-Kreuzberg</strong></a> is the administrative authority of Berlin Friedrichshain-Kreuzberg and is responsible for, among other things, the parking-space management in this area. OpenStreetMap data was already used to support this management and volunteers helped the Bezirksamt by further investigating the data to visualize potentials and specific needs of the district.</p><p>Volunteers enriched the provided datasets by including demographic information about the people living in Friedrichshain-Kreuzberg. Furthermore, they investigated different questions related to the availability of parking spots in different areas. One example was to look at how many parking spots are provided for disabled people. Results indicated that there are appropriate spots but they are rather unevenly distributed within the Bezirk. Another example was to investigate the ratio of cars registered to parking spots available. As you can see in the following graphic, this proportion varies highly among different areas in Friedrichshain-Kreuzberg.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/850/1*exkL-619Nlaj2FTDzKtaxw.png" /><figcaption>The analysis of the parking situation in Friedrichshain-Kreuzberg</figcaption></figure><p>We are happy that our first fully virtual datathon was such a success and that so many talented people decided to spend their weekend working on important social issues. We are also very grateful for the non-profit organizations, our sponsors, and data ambassadors who invested time and energy to make this event possible.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*VrdcMzOiyoTHNwHBuYNelg.png" /></figure><p><em>Authors: Lisa Zäuner, Vadim Voskresenskii</em></p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=8725ed153272" width="1" height="1" alt=""><hr><p><a href="https://medium.com/dssg-berlin-blog/dssg-datathon-2021-organizing-datathon-in-online-format-8725ed153272">DSSG Datathon 2021: Organizing an online Datathon</a> was originally published in <a href="https://medium.com/dssg-berlin-blog">DSSG Berlin Blog</a> on Medium, where people are continuing the conversation by highlighting and responding to this story.</p>]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[DSSG Datathon 2019: Ein ganzes Wochenende lang Datenanalyse fürs Gemeinwohl]]></title>
            <link>https://medium.com/dssg-berlin-blog/dssg-datathon-2019-ein-ganzes-wochenende-lang-datenanalyse-f%C3%BCrs-gemeinwohl-4ec6ffa95aec?source=rss----7d22a7d5aea5---4</link>
            <guid isPermaLink="false">https://medium.com/p/4ec6ffa95aec</guid>
            <dc:creator><![CDATA[krasch]]></dc:creator>
            <pubDate>Mon, 03 Jun 2019 18:52:33 GMT</pubDate>
            <atom:updated>2019-06-03T11:02:59.261Z</atom:updated>
            <content:encoded><![CDATA[<p>Der vierte Data Science for Social Good Berlin Datathon fand Ende April 2019 statt. Dieses Mal dabei: 3 gemeinnützige Organisationen mit Datenfragen und 35 Datenanalyst*innen, die mit ihrem Wissen helfen wollen. Das Besondere am Datathon: gemeinnützige Organisationen und Datenanalyst*innen arbeiten das gesamte Wochenende eng zusammen — diskutieren, tauschen sich aus, lernen voneinander.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*X2I0poWCNPZj_MPdyTGGzA.jpeg" /></figure><blockquote>“Ganz unabhängig von den Ergebnissen war schon der Austausch mit so vielen engagierten Expert*innen und die analytische Herangehensweise an die Problematik eine bereichernde Erfahrung für Christine und mich. Das Format, um NGOs/NPOs mit Datenexpert*innen zusammenzubringen halte ich wirklich für sehr sinnvoll und vielleicht sogar notwendig.” (Jakob Filzen, Start with a Friend)</blockquote><p>Wir stellen hier als erstes die drei diesjährigen Projekte und deren Resultate vor. Danach erzählen wir noch ein bisschen zur Vor- und Nachbereitung eines solchen Datathons. Und wer Interesse bekommen hat, auch mal bei sowas mitzumachen (ob als gemeinnützige Organisation oder als Data Scientist), scrollt bitte ganz nach unten, da gibt es alle Infos.</p><h3>Studieren Ohne Grenzen</h3><p><a href="https://www.studieren-ohne-grenzen.org/">Studieren Ohne Grenzen</a> ist ein studentischer Verein, der Stipendien an bedürftige Student*innen in Konfliktgebieten vergibt. Ziel ist die Verbesserung der Bildungsinfrastruktur vor Ort und eine Sensibilisierung der deutschen Öffentlichkeit für die Lage in den Zielregionen. Jedes Jahr befragt Studieren Ohne Grenzen die Stipendiat*innen mittels Fragebögen zu ihren Erfahrungen mit dem Stipendienprogramm. Während des Datathons wurden diese ausgewertet und dabei unter anderem folgende Einsichten gewonnen:</p><ul><li>Einige Gruppen von Stipendiat*innen haben höhere Abbruchquoten — hier gibt es eventuell Möglichkeiten, für Studieren Ohne Grenzen zeitiger gegenzusteuern.</li><li>Mit Hilfe von Textanalyse / topic modeling konnten die Datenanalyst*innen interessante neue Informationen aus langen Antworten extrahieren.</li><li>Dank einer Analyse von Qualität und Länge der Antworten konnten konkrete Hinweise zur Verbesserung des Fragebogendesigns gegeben werden.</li></ul><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/0*rkWQAAJ0kiexMXbz" /></figure><h3>facebook.tracking.exposed</h3><p><a href="https://facebook.tracking.exposed/">tracking.exposed </a>will mehr Transparenz schaffen über Personalisierungsalgorithmen wie sie zum Beispiel von facebook eingesetzt werden. Dafür hat tracking.exposed ein Browserplugin entwickelt, mit Hilfe dessen interessierte Nutzer*innen anonymisierte Daten zu ihrer facebook-timeline an tracking.exposed “spenden” können. Entstanden ist eine enorme Datenbank, die Wissenschaftler*innen kostenfrei zur Verfügung steht. Während des Datathons entwickelten die Datenanalyst*innen unter anderem:</p><ul><li>Eine Methode zur Messung der Ähnlichkeit der Timeline zweier facebook-Nutzer*innen.</li><li>Ein Tool zur Identifikation von Worten / Phrasen, die plötzlich viel öfter verwendet werden als noch vor wenigen Tagen. Das Wissen um solche “Trendworte” hilft beispielsweise bei der Analyse von Filterblasen.</li><li>Die Analyse der Stimmung von Nutzer*innen über die Zeit, dazu mehr in <a href="https://medium.com/@mwg_89108/outsmarting-algorithms-95e68436dacchttps://facebook.tracking.exposed/">diesem Blogpost</a>.</li></ul><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/0*nuYtqBK7sE7_oWIM" /></figure><blockquote>“<em>The group I represented at the datathon is a bit atypical: we know how to collect and manage data, but we lack the typical tools to analyse it. Since our goal is exploring the impact of algorithms on the information workflow, we needed some external support. My experience at the datathon has been successful, not only because data scientists used their creativity to figure out new methods of seeing data, but also because the code produced is going to be integrated into our free software project</em>.” (Claudio Agosti, tracking.exposed)</blockquote><h3>Start with a friend</h3><p><a href="https://www.start-with-a-friend.de/">Start with a Friend</a> vermittelt Tandems zwischen Geflüchteten und Einheimischen. Der Anspruch ist, dass Tandems auf Augenhöhe stattfinden und beide Seiten voneinander lernen können. Entsprechend herausfordernd ist das Zusammenstellen passender Tandems. Beim Datathon untersuchten Datenanalyst*innen eine Reihe von Fragestellungen rund um das Thema Tandemqualität und -findung. Die Analyst*innen…</p><ul><li>werteten Umfang und Qualität der vorhandenen Daten aus (insbesondere im Hinblick auf eine vor kurzem stattgefundene Umstellung der Datenbank) und gaben konkrete Hinweise zur weiteren Verbesserung der Datenbank.</li><li>kamen zu dem Schluss, dass es mit den aktuell vorhandenen Daten kaum möglich ist, vorher einzuschätzen, ob ein Tandem langlebig werden könnte oder nicht.</li><li>extrahierten Stimmungen (positiv, neutral, negativ) aus Volltext-Kommentarfeldern um besser einschätzen zu können, ob es sich um ein erfolgreiches Tandem handelt.</li></ul><p>Die Erkenntnisse werden von Start with a Friend genutzt, um die Weiterentwicklung ihrer Datenbank zu steuern.</p><h3>Was passiert vor und nach dem Datathon?</h3><p>Wir führen mit interessierten gemeinnützigen Organisationen zunächst immer ein kurzes Erstgespräch, entweder persönlich oder am Telefon. Stellt sich heraus, dass eine interessante Zusammenarbeit möglich sein könnte, organisieren wir einen Abendworkshop zu dem wir auch ein bis zwei zum Thema passende Expert*innen einladen (wir nennen sie Datenbotschafter*innen). Während des Workshops loten wir aus, welche Analysen möglich sind und sich für einen Datathon eignen.</p><p>In Vorbereitung auf den Datathon stehen die Datenbotschafter*innen der gemeinnützigen Organisation bei allen Fragen zur Seite und kümmern sich um die Vorbereitung und Anonymisierung der Daten. Nach dem Datathon fassen die Datenbotschafter*innnen die Resultate in einem Bericht zusammen und helfen bei der Planung der nächsten Schritte.</p><h3>Zusammenarbeit mit DSSG Berlin</h3><p>Für gemeinnützige Organisationen: Interesse an einem Erstgespräch bekommen? Einfach eine kurze E-mail an <a href="/service/mailto:contact@dssg-berlin.org">contact@dssg-berlin.org</a> und wir melden uns direkt!</p><p>Für Data Scientists: Schick eine kurze E-mail an <a href="/service/mailto:volunteer@dssg-berlin.org">volunteer@dssg-berlin.org</a> mit ein paar Infos zu deinem Background. Dann kommst du auf die Volunteerliste, an die wir unsere Einladungen zu Projekten schicken.</p><h3>Danke!</h3><p>Es war mal wieder ein tolles Wochenende und wir sind froh, dass auch dieses Mal soviele Datenanalyst*innen ihr Wochenende für unsere Partnerorganisationen gespendet haben. Danke! Besonderer Dank natürlich an unsere Partnerorganisationen und Datenbotschafter*innen. Danke an die vielen Helfer*innen die uns bei der Organisation und der Durchführung des Events unterstützt haben.</p><p>Und natürlich vielen Dank auch an unsere Sponsoren:</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*RFtJhYSGmpzY9JPCcqakSg.png" /></figure><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=4ec6ffa95aec" width="1" height="1" alt=""><hr><p><a href="https://medium.com/dssg-berlin-blog/dssg-datathon-2019-ein-ganzes-wochenende-lang-datenanalyse-f%C3%BCrs-gemeinwohl-4ec6ffa95aec">DSSG Datathon 2019: Ein ganzes Wochenende lang Datenanalyse fürs Gemeinwohl</a> was originally published in <a href="https://medium.com/dssg-berlin-blog">DSSG Berlin Blog</a> on Medium, where people are continuing the conversation by highlighting and responding to this story.</p>]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Inside the Data Ambassador role in DSSG]]></title>
            <link>https://medium.com/dssg-berlin-blog/inside-the-data-ambassador-role-in-dssg-29ae374a5c23?source=rss----7d22a7d5aea5---4</link>
            <guid isPermaLink="false">https://medium.com/p/29ae374a5c23</guid>
            <category><![CDATA[machine-learning]]></category>
            <category><![CDATA[data-for-good]]></category>
            <category><![CDATA[data-science]]></category>
            <dc:creator><![CDATA[Dânia Meira]]></dc:creator>
            <pubDate>Wed, 02 Jan 2019 09:10:27 GMT</pubDate>
            <atom:updated>2019-01-02T09:10:11.981Z</atom:updated>
            <content:encoded><![CDATA[<h3>Data Ambassador at DSSG Berlin</h3><p>It was around mid-2016 when I had been doing data science for a couple of years, first in Brazil and then in Germany. And I was proud to have applied much of the theory and techniques learned during my studies into solving real-life problems.</p><p>Up until then I had worked mainly in projects related to understanding user behavior, for instance finding meaningful clusters and segments of users, developing models for churn prediction and also for cross- and up-selling, applying recommendation systems techniques to personalize user experience in a platform, monitoring social media channels for understanding customer satisfaction and engagement with a brand…</p><h3>Why Data Science for Social Good ?</h3><figure><img alt="" src="https://cdn-images-1.medium.com/max/225/0*7EvjR2GId_2o5WDn" /></figure><p>In all of those projects, the creative and critical thinking combined with technical skills lead to finding insights and meaningful relationships between trends, products, and behaviors. This positive impact combined with my desire to contribute meaningfully, and I started to look for ways I could help promote the betterment of our world.</p><p>I found out about <a href="https://dssg-berlin.org/">DSSG Berlin</a> in April 2016 when I attended a Data Science event in the city. They exist since 2015, and have partnered with more than 20 nonprofits and more than 100 pro bono data scientist to find solutions for social problems. The way to accomplish this is by organizing a range of events spanning from <a href="https://blog.dssg-berlin.org/data-science-office-hours-on-june-5th-and-mini-social-688f02ad4d15">Office Hours</a>, <a href="https://blog.dssg-berlin.org/data-science-speed-dating-in-berlin-9c75a44a5c00">Speed Dating</a> to <a href="https://blog.dssg-berlin.org/data-analysis-for-vocational-orientation-and-cancer-knowledge-management-3e73e5dc4357">Datathons</a>.</p><h3>How did I get involved?</h3><p>I applied to DSSG Berlin in May 2016 and in this occasion I was added to their volunteer database. Then, as soon as there is a new project all of us in this database receive a call for volunteers related to a specific project. In August, they announced to be looking for a team of Data Ambassadors for a NLP and Visualization project with the Deutsche Krebsgesellschaft (German Cancer Society). That seemed interesting and it fit my skill set, so I applied. Good news came soon: I got selected to participate alongside with another volunteer with Data Engineering background . Yey !</p><h3>What are Data Ambassadors?</h3><p>A Data Ambassador is a volunteer at the interface between participants of a Datathon and the NPO that is looking for a data solution. There are usually 1–3 ambassadors per project and this group gets assigned a representative of the partner organization for questions.</p><p>Most of the work is done in preparation for the Datathon. It starts 2 to 3 months before the event, when getting in contact with the NPO to talk about their challenge, possible solutions and the data they can/want to provide. Though the following weeks the team is iterating on the proposal, working with the organization in a collaborative way to more clearly define the problems possible to be solved with the given data. After having a look at the data and doing basic cleansing (e.g. : check date format, string encoding, take care of normalization, duplicated information and data consistency) it is possible to use it to evaluate potential analyses and strategies. The data ambassadors communicate such ideas to the organization’s representative and collects feedback, when available also more data. This is done until a satisfactory proposal is reached. In this stage, it’s important to manage expectations from the NPO.</p><p>During the Datathon, the team is guiding the participants who opted to work on the project, and after they help wrapping up the project and get results into a usable format for the nonprofit.</p><h3>The NPO: Deutsche Krebsgesellschaft</h3><figure><img alt="" src="https://cdn-images-1.medium.com/max/133/0*RiB3SKgvUR4a76II" /></figure><p>The <a href="https://www.krebsgesellschaft.de/">Deutsche Krebsgesellschaft</a> is Germany’s largest oncological society/association. The knowledge and information management team at DKG works on building a knowledge base covering studies and meta analyses published in the last ten years on the topic of solid cancers like breast and colorectal or prostate cancer. To this end, they scan the medical databases OVID and EBCSO, extract publication metadata and pdf, and add keywords identifying the tumor and focus (e.g. diagnostic, therapy) of the studies. The knowledge base is currently being used by counselors working at the Deutsche Krebshilfe phone hot-line for patients and their relatives. Hotline Website: <a href="https://www.infonetz-krebs.de/">https://www.infonetz-krebs.de/</a></p><h3>Project Timeline</h3><h4><strong>Six months preparation for the Datathon weekend (October 2016 to March 2017)</strong></h4><blockquote><em>Main tasks:</em> Problem definition, cleaning and joining of data.</blockquote><blockquote><em>Main goal</em>: guaranteeing to provide clean data and well defined problems to the volunteers in order to enable them to fully concentrate on working on the solution.</blockquote><p>On average we worked 3–4h / week on the project. Besides us 2 volunteers assigned for this project specifically, we also counted with the support of the main DSSG Berlin team. Katharina Rasch acted as supervisor and also a mediator between the team of Data Ambassadors and The Deutsche Krebsgesellschaft (DKG).</p><p>On the kickoff meeting between DSSG Berlin and DKG we got a good first understanding of the status-quo. There is an exponentially growing body of work in oncology at the same time as many unsolved systematic questions that result in a poor comparability between studies (e.g. studies differ in context, specific vocabulary, etc). As a result, it is no longer possible for doctors, patients or relatives to thoroughly analyze the amount of available scientific publications and other information. Their main pain point is the need to deploy a tremendous amount of resources for a comprehensive, scientific analysis of the available publications while in reality they have only a few limited resources to read, process, find links and catalogue scientific literature on cancer.</p><p>But still, many documents need to be labeled to enable hotline to provide most up-to-date support &amp; information about cancer treatment. At the time, the strategy implemented was a “four-eye-principle” : two people label the same scientific publication independently. They were motivated to partner up with DSSG Berlin to investigate if there is an opportunity to relief the workload by leveraging AI.</p><p>We created a slack channel to enable quick and direct communication between the DSSG Berlin and DKG teams. There they also could share some small subsets of data with us, so we could start drafting some solutions and thus make the task for Datathon less abstract. We got 100 PDFs as example because we interpreted their challenge as a knowledge extraction one, the following strategy was suggested:</p><blockquote>1) Transform the unstructured PDFs to unstructured raw text — but still needed to confirm if it was possible, would try it with the first random sample of 100 files.</blockquote><blockquote>2) Transform the unstructured raw text into structured text by using some information extraction/NLP algorithm. We wanted to figure out some underlying structure in the text. Examples: clustering the text raw files, using the classification/tags of the scientific papers, filtering specific regular expressions inside each section, …</blockquote><blockquote>3) Transform this structured data into formal knowledge. Using an Ontology, or some other type of semantic analysis.</blockquote><p>They liked this strategy so we started working on it!</p><p>First step was done sooner than later: the data from the PDF files were successfully extracted with java and Apache PDFBox lib. We checked the outcome for consistency and sanity,</p><p>Then we moved on to step 2 by trying standard entity recognition extraction with Rapid Miner and the extension AYLIEN. It was able to find some entities, but only the ones it was trained for such as places, date and location which didn’t help us that much.</p><p>One other idea still on step 2 was to search for specific terms in the text, if those were given by the DKG field specialists. Still, if we had a set of terms/ontology to try to extract, it was not clear how exactly to use that — it would require further investigation on our side too.</p><p>Another independent idea was to move on directly to step 3 and apply topic modelling on the text files using python gensim library. It would allow us to find topics in this corpus.</p><p>Well, we realized at this point that we needed more alignment with DKG. We needed to understand what we wanted to find and which questions we were trying to answer exactly. For that, we scheduled an extra meeting in their office with the goal to get a better understanding what their team was doing with the texts and also to try finding different data they could be using beyond the PDFs.</p><p>It was a very positive meeting in which we could watch how they used their systems (reference manager, text search …) and talk about their internal oncology ontology. We got what we went there for:</p><ul><li>more data: some XML extracts from their reference manager, search terms they used to find the scientific publications, and a set of PDFs processed by them and signaled as containing useful information to be inputted on the internal knowledge database.</li><li>insights on the search and full text screening process, their reference manager, annotations and final knowledge DB, hotline system tool</li><li>understanding when the data was extracted from the record like metadata or search info and when it was provided by manual annotation</li></ul><p>With all of this new information, we had a lot do work with. We iterated between two main tasks:</p><p>1) <em>Processing all the data into a final data set: </em>cleaning up duplication and inconsistencies, removing information from manual annotation when it was not made for the knowledge database task (they are also doing their own scientific work), making some annotation uniform (created patterns on top of the manual annotation), translating labels to English and during the process we worked together with our DKG representative to clarify the meaning of labels and manual annotation.</p><p>2) <em>Drilling down actual idea for the Datathon:</em> We came up with two main tasks: a classification to match the publication to a class true/false — true if it is a relevant result to the search and false if not. And text mining to extract better features from the text to improve the classification above.</p><p>We then worked on a simple implementation for the tasks above, to check if it was doable at all.</p><p>On the month preceding the weekend event, we managed to extract features from XMLs and use such to implement a basic baseline classification.</p><p>Also we had a better definition of tasks to be proposed during the Dathaton, from the clearer and simpler to more complicated and abstract ones:</p><ol><li><em>Classify the publication documents as either relevant result or not</em></li><li><em>Predict the structure in the ontology the publication belongs to</em></li><li><em>Use text extraction from publication to enhance the quality of 1. or 2.</em></li><li><em>Inspirational Tasks: Cluster documents, find links between them or, flag similar documents.</em></li></ol><p>But we were still missing some data to make those tasks fully achievable, while still needed to figure out some organizational things like how would we provide the data at the dive and how would we deal with the legacy issues about the scientific publications.</p><p>On the first weeks of March, before we had our Datathon, we finally managed to get all the data and answer the organizational questions above.</p><p>Here is the summary of our weeks of working back-and-forth with the DKG:</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*ZBPTjQsV0ngy6J4dv616JA.png" /><figcaption><em>Refining and reframing the questions </em>so they enable appropriate data science solutions while bringing relevant value to DKG</figcaption></figure><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*sABqxsSPJ98mEv8Y8pEsEA.png" /><figcaption>​Map all available and relevant data sources to to address the questions above</figcaption></figure><h4><strong>March 17th to 19th 2017: Datathon Weekend</strong></h4><p>During that weekend we presented the DKG tasks and available data set to participants. We also pointed the volunteers to the<a href="https://github.com/meiradania/dssg-dkg"> github repo</a> with an example on how to ingest the data, process it with some python NLP related libraries and train the baseline classification model.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/0*iZMznwRPD5hUjhp7" /><figcaption>My presentation about the DKG tasks and baseline solution</figcaption></figure><p>We also encouraged people to form groups (at least 2 people) for working session, preventing the participants from getting demotivated/disappointed, encouraged communication among teams, moderated group discussions and guided breaks.</p><p>By the end of the day, we organized the final presentation session where each team presented its results to the others and the NPO.</p><p>We are proud to present the following solutions around cataloguing scientific literature on cancer:</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/0*D1GlNhvJlNQbAT-l" /><figcaption>DSSG Team and Volunteers at the Datathon</figcaption></figure><ul><li><strong>Group I</strong>: Classification of relevance (binary classifier) and classification of cancer type (multilabel classifier) with with logistic regression, xgboost and LSTM.</li><li><strong>Group II</strong>: Cancer type classification with active learning and multilabel loss.</li><li><strong>Group III</strong>: Finding hidden topics in the DKG corpus: duplicated articles, new labels on existing articles, new grouping with more meaning, prioritizing articles if RCT or Case Series type.</li><li><strong>Group IV</strong>: Classification of relevance by indexing scientific publication on Elastic Search and running k-nearest-neighbors.</li><li><strong>Group V</strong>: Enriched the DKG corpus with data from clinicaltrials.gov</li><li><strong>Group VI</strong>: Enriched the DKG corpus by annotating text with NER + visualisation in Kibana.</li></ul><h4><strong>May &amp; June 2017: Follow-up and implementation</strong></h4><p>At this time I was having some family time back in Brazil, so the other Data Ambassador together with Katharina, our DSSG Berlin supervisor, took over the responsibilities to discuss the results with the NPO in a follow-up meeting, making sure they received all the material produced during the Datathon.</p><p>Katharina scheduled a workshop with DKG and two of the Datathon teams. They went again through their cataloguing process and it was great to see how they were able to now more confidently speak about were they see possibilities for data science / automatization. Specifically, they decided to move from a four-eye-principle (two people label the same article independently) to a two-eye+computer principle (i.e. replace one of the humans with the classifier). An enhanced version of the classifier created during the Datathon is currently in beta-test with the DKG. The necessary data infrastructure is being set up by one of the Datathon teams as a consulting project.</p><h4>Final Note</h4><p>I so enthused to have played a part in what ended up being such a fruitful project, that it made me yearn for more of these sort of collaboration. It inspired me and that’s is why today I am a member of the core DSSG Berlin team. Currently I’m supporting them with volunteer management and assessment, also by building up knowledge about of the Data Ambassador responsibilities both internally via documentation as well as externally by publishing this story :)</p><p>Reach out at <a href="/service/mailto:volunteer@dssg-berlin.org">volunteer@dssg-berlin.org</a> if it sparked your curiosity!</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=29ae374a5c23" width="1" height="1" alt=""><hr><p><a href="https://medium.com/dssg-berlin-blog/inside-the-data-ambassador-role-in-dssg-29ae374a5c23">Inside the Data Ambassador role in DSSG</a> was originally published in <a href="https://medium.com/dssg-berlin-blog">DSSG Berlin Blog</a> on Medium, where people are continuing the conversation by highlighting and responding to this story.</p>]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Data Science Office hours on June 5th (and mini social)]]></title>
            <link>https://medium.com/dssg-berlin-blog/data-science-office-hours-on-june-5th-and-mini-social-688f02ad4d15?source=rss----7d22a7d5aea5---4</link>
            <guid isPermaLink="false">https://medium.com/p/688f02ad4d15</guid>
            <category><![CDATA[data-science]]></category>
            <dc:creator><![CDATA[Chris Adams]]></dc:creator>
            <pubDate>Mon, 04 Jun 2018 12:14:44 GMT</pubDate>
            <atom:updated>2018-06-04T12:12:57.373Z</atom:updated>
            <content:encoded><![CDATA[<p><em>Do you work in a non-profit and want some help thinking through how you<br>use data in your organization? Once again, Data Science for<br>Social Good Berlin is running pro-bono office hours for non-profits<br>at </em><a href="https://berlin.impacthub.net/"><em>ImpactHub Berlin</em></a><em>.</em></p><h4>How do office hours work?</h4><p>At the office hours, you will be paired with a data<br>scientist for 25 minutes, to help you think through your data problem, and the options available to you, you’ll discuss topics such as:</p><p>- How can we measure the impact of our organization?<br>- How can we best prioritize where we should put our resources?<br>- How can we use data science to automate annoying manual work?<br>- Anything else data-related you are wondering about</p><h4>When do these take place?</h4><p>The office hours usually take place every first Tuesday evening of the<br>month, hosted by our lovely friends at <a href="https://berlin.impacthub.net/">Impact Hub Berlin</a>.</p><p>You can sign up for our next session on June 5th here:</p><h4><a href="https://www.eventbrite.de/e/dssg-berlin-datensprechstunde-office-hours-june-2018-tickets-45736830090">https://www.eventbrite.de/e/dssg-berlin-datensprechstunde-office-hours-june-2018-tickets-45736830090</a></h4><h4>I can’t make this one, but I still want to come!</h4><p>If you can’t make this one, you can join our mailing list, to find out when our next events are taking place (spoiler — we run these every month now, and we have more events coming).</p><h4>What’s this mini social thing too?</h4><p>While we <em>do</em> run the office hours in an an office, Impact Hub is big enough for for you to come along, and meet others if you’re just interested in what we do, so we’re also trying out with running a meet and greet, to get to know some new faces.</p><p>So if you’re a data scientist interested in learning how you can volunteer, or from an NGO and curious, you’re welcome to drop by.</p><p>See you there!</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=688f02ad4d15" width="1" height="1" alt=""><hr><p><a href="https://medium.com/dssg-berlin-blog/data-science-office-hours-on-june-5th-and-mini-social-688f02ad4d15">Data Science Office hours on June 5th (and mini social)</a> was originally published in <a href="https://medium.com/dssg-berlin-blog">DSSG Berlin Blog</a> on Medium, where people are continuing the conversation by highlighting and responding to this story.</p>]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[10. April: Datensprechstunde für gemeinnützige Organisationen]]></title>
            <link>https://medium.com/dssg-berlin-blog/10-april-datensprechstunde-f%C3%BCr-gemeinn%C3%BCtzige-organisationen-f870106eb01?source=rss----7d22a7d5aea5---4</link>
            <guid isPermaLink="false">https://medium.com/p/f870106eb01</guid>
            <dc:creator><![CDATA[krasch]]></dc:creator>
            <pubDate>Tue, 03 Apr 2018 14:08:12 GMT</pubDate>
            <atom:updated>2018-04-03T14:08:11.674Z</atom:updated>
            <content:encoded><![CDATA[<p>Fast jede gemeinnützige Organisation hat eine Datenbank in der sie die Daten von Spendern, Mitgliedern, Ehrenamtlichen und viele andere nützliche Informationen sammelt. Aber die wenigsten Organisationen sind sich bewusst, dass man anhand dieser Daten noch weitere Informationen herausarbeiten oder sogar Handlungsstrategien ableiten kann.</p><p>Wir (Data Science For Social Good Berlin) sind eine Initiative aus erfahrenen DatenanalystInnen, die sich neben ihrer beruflichen Tätigkeit ehrenamtlich engagieren wollen. Unter anderem bieten wir einmal monatlich eine Sprechstunde zum Thema “Datenanalyse” an.</p><p>In dieser können beispielsweise folgende Fragen diskutiert werden:</p><p>- Wie können wir die Wirkung unserer Organisation messbar machen?<br>- Wie können wir unsere Ressourcen besser priorisieren?<br>- Ist es möglich, nervige manuelle Prozesse in unserer Organisation teilzuautomatisieren?<br>- Und natürlich alle anderen Fragen zum Thema Daten und Datenanalyse.</p><p>Die Sprechstunde findet jeden ersten Dienstagabend des Monats statt (Ausnahme im April wegen Ostern). Zum Mitmachen, einfach hier anmelden: <a href="http://bit.ly/datensprechstunde-april-2018">http://bit.ly/datensprechstunde-april-2018</a>. Wir melden uns dann in Kürze mit weiteren Information. Im April keine Zeit? Einfach für unseren <a href="https://dssg-berlin.org/#newsletter">Newsletter</a> anmelden!</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=f870106eb01" width="1" height="1" alt=""><hr><p><a href="https://medium.com/dssg-berlin-blog/10-april-datensprechstunde-f%C3%BCr-gemeinn%C3%BCtzige-organisationen-f870106eb01">10. April: Datensprechstunde für gemeinnützige Organisationen</a> was originally published in <a href="https://medium.com/dssg-berlin-blog">DSSG Berlin Blog</a> on Medium, where people are continuing the conversation by highlighting and responding to this story.</p>]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[It’s that time again — data science office hours at Impact Hub Berlin in April]]></title>
            <link>https://medium.com/dssg-berlin-blog/its-that-time-again-data-science-office-hours-at-impact-hub-berlin-in-april-7c163701b31e?source=rss----7d22a7d5aea5---4</link>
            <guid isPermaLink="false">https://medium.com/p/7c163701b31e</guid>
            <category><![CDATA[data-science]]></category>
            <dc:creator><![CDATA[Chris Adams]]></dc:creator>
            <pubDate>Tue, 03 Apr 2018 12:55:32 GMT</pubDate>
            <atom:updated>2018-04-03T13:11:20.801Z</atom:updated>
            <content:encoded><![CDATA[<p><em>Do you work in a non-profit and want some help thinking through how you<br>use data in your organization? Once again, Data Science for<br>Social Good Berlin is running pro-bono office hours for non-profits<br>at </em><a href="https://berlin.impacthub.net/"><em>ImpactHub Berlin</em></a><em>.</em></p><h4>How do office hours work?</h4><p>At the office hours, you will be paired with a data<br>scientist for 25 minutes, to help you think through your data problem, and the options available to you, you’ll discuss topics such as:</p><p>- How can we measure the impact of our organization?<br>- How can we best prioritize where we should put our resources?<br>- How can we use data science to automate annoying manual work?<br>- Anything else data-related you are wondering about</p><h4>When do these take place?</h4><p>The office hours usually take place every first Tuesday evening of the<br>month, hosted by our lovely friends at <a href="https://berlin.impacthub.net/">Impact Hub Berlin</a>.</p><p>You can sign up for our next session on April 10th here:</p><h4><a href="http://bit.ly/datensprechstunde-april-2018">http://bit.ly/datensprechstunde-april-2018</a></h4><h4>I can’t make this one, but I still want to come!</h4><p>If you can’t make this one, you can join our mailing list, to find out when our next events are taking place (spoiler — we run these every month now, and we have more events coming).</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=7c163701b31e" width="1" height="1" alt=""><hr><p><a href="https://medium.com/dssg-berlin-blog/its-that-time-again-data-science-office-hours-at-impact-hub-berlin-in-april-7c163701b31e">It’s that time again — data science office hours at Impact Hub Berlin in April</a> was originally published in <a href="https://medium.com/dssg-berlin-blog">DSSG Berlin Blog</a> on Medium, where people are continuing the conversation by highlighting and responding to this story.</p>]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Roll up, roll up! Data science Speed Dating at Co-up Berlin on March 22nd!]]></title>
            <link>https://medium.com/dssg-berlin-blog/roll-up-roll-up-data-science-speed-dating-at-co-up-berlin-on-march-22nd-c89721d27c44?source=rss----7d22a7d5aea5---4</link>
            <guid isPermaLink="false">https://medium.com/p/c89721d27c44</guid>
            <category><![CDATA[data-science]]></category>
            <category><![CDATA[dssg-berlin]]></category>
            <dc:creator><![CDATA[Chris Adams]]></dc:creator>
            <pubDate>Wed, 14 Mar 2018 16:55:36 GMT</pubDate>
            <atom:updated>2018-03-14T17:12:00.530Z</atom:updated>
            <content:encoded><![CDATA[<p>Last year, <a href="https://blog.dssg-berlin.org/data-science-speed-dating-in-berlin-9c75a44a5c00">we tried out an event, Data Science Speed Dating</a>, where we matched up non-profit organisations with volunteer data analysts and data scientists in a speed dating type of event.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*EgBxN4PSLRDS4Iv_Q4NnEw.jpeg" /></figure><p>It seemed to go down well last time <a href="https://blog.dssg-berlin.org/data-science-speed-dating-in-berlin-9c75a44a5c00">(read our write up here)</a>, so we’re doing our next one on <strong><em>Thursday 22nd March 2018, </em></strong>at co-up, everybody’s favourite nerd Berlin community space.</p><h4>Wait, why would I even go to this?</h4><p><strong>If you’re good at working with data</strong>, you get to use your skills for something socially useful, meet nice people, and understand problems outside your day-to-day.</p><p><strong>If you’re in a non-profit organisation</strong>, you get access to the insight and experience of a load of expensive people thinking about a thorny data problem you’re wrestling with, who you couldn’t typically afford. And you meet loads of nice people.</p><p>Everyone wins!</p><h4>Okay, that sounds cool. Where do I sign up?</h4><p>You can <a href="http://tickets-43546017310/">sign up on eventbrite</a> — and if you can’t make it, help make the world a better place and either let a data savvy friend now, or send a non-profit our way.</p><p>Thanks, and see you on the 22nd.</p><h4><a href="https://www.eventbrite.de/e/dssg-data-science-speed-dating-march-2018-tickets-43546017310">Still here? Why are you not signing up?</a></h4><p>P.S If you’re hiring, and you’re up for helping us cover the cost of the food (it was about 100 EUR for 30 people last time), <a href="/service/mailto:contact@dssg-berlin.org"><em>we’d love to chat</em></a><em> — drop us a line at contact@dssg-berlin.org</em>.</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=c89721d27c44" width="1" height="1" alt=""><hr><p><a href="https://medium.com/dssg-berlin-blog/roll-up-roll-up-data-science-speed-dating-at-co-up-berlin-on-march-22nd-c89721d27c44">Roll up, roll up! Data science Speed Dating at Co-up Berlin on March 22nd!</a> was originally published in <a href="https://medium.com/dssg-berlin-blog">DSSG Berlin Blog</a> on Medium, where people are continuing the conversation by highlighting and responding to this story.</p>]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Roll up, roll up! Data science office hours at ImpactHub Berlin in March!]]></title>
            <link>https://medium.com/dssg-berlin-blog/roll-up-roll-up-data-science-office-hours-at-impacthub-berlin-in-march-8c7df8951341?source=rss----7d22a7d5aea5---4</link>
            <guid isPermaLink="false">https://medium.com/p/8c7df8951341</guid>
            <category><![CDATA[data-science]]></category>
            <dc:creator><![CDATA[Chris Adams]]></dc:creator>
            <pubDate>Tue, 20 Feb 2018 15:45:18 GMT</pubDate>
            <atom:updated>2018-02-20T15:45:17.690Z</atom:updated>
            <content:encoded><![CDATA[<p><em>Do you work in a non-profit and want some help thinking through how you<br>use data in your organization? Starting in March, Data Science for<br>Social Good Berlin will be running pro-bono office hours for non-profits<br>at </em><a href="https://berlin.impacthub.net/"><em>ImpactHub Berlin</em></a><em>.</em></p><h4>How do office hours work?</h4><p>At the office hours, you will be paired with a data<br>scientist for 25 minutes, to help you think through your data problem, and the options available to you, you’ll discuss topics such as:</p><p>- How can we measure the impact of our organization?<br>- How can we best prioritize where we should put our resources?<br>- How can we use data science to automate annoying manual work?<br>- Anything else data-related you are wondering about</p><h4>When do these take place?</h4><p>The office hours will take place every first Tuesday evening of the<br>month, hosted by our lovely friends at <a href="https://berlin.impacthub.net/">Impact Hub Berlin</a>.</p><p>You can sign up for the first one, happening on March 6th here:</p><h4><a href="http://bit.ly/dssg-office-hours">http://bit.ly/dssg-office-hours</a></h4><h4>I can’t make this one, but I still want to come!</h4><p>If you can’t make this one, you can join our mailing list, to find out when our next events are taking place ( spoiler — we run these every month now, and we have more events coming).</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=8c7df8951341" width="1" height="1" alt=""><hr><p><a href="https://medium.com/dssg-berlin-blog/roll-up-roll-up-data-science-office-hours-at-impacthub-berlin-in-march-8c7df8951341">Roll up, roll up! Data science office hours at ImpactHub Berlin in March!</a> was originally published in <a href="https://medium.com/dssg-berlin-blog">DSSG Berlin Blog</a> on Medium, where people are continuing the conversation by highlighting and responding to this story.</p>]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Data Science Speed Dating in Berlin in 2017]]></title>
            <link>https://medium.com/dssg-berlin-blog/data-science-speed-dating-in-berlin-9c75a44a5c00?source=rss----7d22a7d5aea5---4</link>
            <guid isPermaLink="false">https://medium.com/p/9c75a44a5c00</guid>
            <category><![CDATA[data-science]]></category>
            <category><![CDATA[data-for-good]]></category>
            <dc:creator><![CDATA[Chris Adams]]></dc:creator>
            <pubDate>Wed, 14 Feb 2018 13:57:51 GMT</pubDate>
            <atom:updated>2018-03-14T14:00:26.693Z</atom:updated>
            <content:encoded><![CDATA[<p><em>We’ve been running various kinds of data science themed events with non-profits since DSSG Berlin was set up back in 2015. Towards the end of last year, we tried out a new kind of event, which we’re calling </em><strong><em>Data Science Speed Dating, </em></strong><em>and it seemed to work out well</em><strong><em>. </em></strong><em>Read on find out more, how it works, and how to sign up for the next one.</em></p><h3>Data Science Speed Dating? What’s the big idea?</h3><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*EZS-MGzRo-07rUD5raG1og.jpeg" /></figure><p>In short, we want to make it easy for non profit organisations to speak to volunteer data scientists so they can help them think through data problems as early as possible.</p><p><strong>Share the problem</strong></p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*nzkQaec-0KdE97EVL2xU4w.jpeg" /></figure><p>So, rather than waiting until we have all the data, and a really well defined brief, each non-profit organisation had a chance to present their problem for 5 minutes, to a room of volunteer data scientists.</p><p><strong>Think through it together</strong></p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*-g8SttwCBXUWeqcITsuLSA.jpeg" /></figure><p>Next, each non-profit organisation was paired with a table of data scientists, and had 10 minutes to explore the problem together, completing a worksheet with prompts, to talk about:</p><ul><li>common problems that they have come across on previous projects</li><li>metrics to track so the non-profit can see if they’re making progress</li><li>what kind of resources this project would need, so they know early if they need to rethink the scope</li></ul><p><strong>The speed dating part</strong></p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*uVCCTBncoKmypIxRXSWIdg.jpeg" /></figure><p>After 10 minutes was up, we introduced the speed dating part — we rotated the groups, matching the data scientist volunteers to a new non-profit, and repeated the process, until all the volunteers had spoke to all the non-profits.</p><p>By the end of the night, people from the non profits had a chance to think through their problem with nearly 25–30 skilled data professionals, leaving the event with a load of useful, structured feedback about the next steps they should take.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*RFkPmhciMquMOTfZjm97jQ.jpeg" /></figure><p>If any volunteers or nonprofits get on particularly well together, the worksheets allowed a chance for data scientists to opt-in for a single follow up coffee to discuss in more detail.</p><h3>Okay, but why would you need this?</h3><p>Many non profits we speak to don’t have the expertise or skills in-house to prepare a really well-defined data problem by themselves, nor do they have the data collated in a way data scientists can work on straight away. So, before data scientists can do any actual analysis, it ends up taking a lot of volunteer time to help collate data, clean it up, and work out how to explain the problem to others, before its possible to have an event like a hackday or similar where you might try solving the problem. This limits how many non-profits we can help.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*QWg4TRC0ldAtxMe3TOfklA.jpeg" /></figure><p>In many cases, what’s more useful is for someone proficient at working with data to help people from the non-profit organisation think about the problem at the beginning — so they know what kind of data they need to collect, how they need to store it, so and what can realistically be done with data in the first place.</p><p>You don’t need a long data science project to help people in an non-profit organisation to think about this — you just need timely access to right person, early.</p><h3>Alright that sounds kinda neat. You doing stuff like this again?</h3><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*42I04rV72NcwiFdHNwDBaw.jpeg" /></figure><p><strong>Yes! And you can totally get involved!</strong></p><p>We have a big hackathon event planned later in spring, but in the meantime, we’re running another <em>Data Science Speed Dating</em> event again on March 22nd, <a href="https://www.eventbrite.de/e/dssg-data-science-speed-dating-march-2018-tickets-43546017310">you can sign up here</a>.</p><p>If this sounds interesting to you, <a href="https://dssg-berlin.org/">sign up to our mailing list to find out when and where</a> future ones will be happening, or follow us on twitter at <a href="https://twitter.com/dssgber">dssgber</a>.</p><h3>Anything else?</h3><p>We’re also trying out running office hours with Impact Hub Berlin, to lower the barrier of entry for getting help.</p><p>If you work in a non-profit organisation, you’re in Berlin, and you’re looking for some advice thinking through a data problem, you can <a href="https://goo.gl/forms/rgdrUmvU1r2QSluv2">book a slot to talk with us, for free, on March 6th</a>.</p><h4><a href="https://goo.gl/forms/rgdrUmvU1r2QSluv2">Book a slot during our office hours session</a></h4><p><strong>If you can’t make it in March</strong></p><p>We’re testing these office hours out, so we only have a few slots available this time, but we’ll be doing this every month through 2018, so it you missed the chance this time, we’ll have another one in in the first week of every month through 2018.</p><p>Once we have the format sorted, we’ll be increasing the numbers of volunteers around to help run these office hours, so we can help more non-profits each month.</p><p>Onward!</p><p><em>Huge thanks to </em><a href="https://twitter.com/toridykes"><em>Tory Dykes</em></a><em> for taking all the photos on the event and the lovely people at c</em><a href="http://co-up.de/"><em>o.up</em></a><em> in Berlin for providing the space to run the event.</em></p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=9c75a44a5c00" width="1" height="1" alt=""><hr><p><a href="https://medium.com/dssg-berlin-blog/data-science-speed-dating-in-berlin-9c75a44a5c00">Data Science Speed Dating in Berlin in 2017</a> was originally published in <a href="https://medium.com/dssg-berlin-blog">DSSG Berlin Blog</a> on Medium, where people are continuing the conversation by highlighting and responding to this story.</p>]]></content:encoded>
        </item>
    </channel>
</rss>