Scenes from a Dive - what’s big data got to do with fighting poverty and fraud?

Photo Credit: Neil Fantom

A more detailed recap will follow soon but here’s a very quick hats off to the about 150 data scientists, civic hackers, visual analytics savants, poverty specialists, and fraud/anti-corruption experts that made the Big Data Exploration at Washington DC over the weekend such an eye-opener. We invite you to explore the work that the volunteers did (these are rough documents and will likely change as you read them so it's okay to hold off if you would rather wait for a ‘final’ consolidated  document). The projects that the volunteers worked on include: 

• Predicting Small-Scale Poverty Measures from Night Illumination - can freely available satellite imagery, showing average nighttime illumination, serve as a reasonable poverty measurement proxy?
• Scraping Websites to Collect Consumption and Price Data - what can researchers studying poverty in countries learn from openly available crowdsourced daily price data, and by scraping price data from supermarket websites?
• Latin America Poverty Analysis from Mobile Surveys - how does the quality of data from mobile survey compare with what is collected through traditional household surveys?
• Measuring Socioeconomic Indicators in Arabic Tweets - can Twitter data help you understand socio-economic trends in countries?
• Analyzing the World Bank’s Project Data for ‘Signals’ - do successful or unsuccessful projects (or projects reporting corruption and the ones that don’t) share any characteristics?
• Analyzing World Bank Supplier Profiles - can the Bank and other agencies include publicly available data to gain a broader, more comprehensive understanding of their suppliers and use the information as proxies for risk management?
• UNDP Resource Allocation - can UNDP use staffing and program budget data to infer what skillsets mix and match the best in projects?
• Social networking analysis for risk measurement - can you forecast project risk using social networking analysis tools?
• Can you use simple heuristic auditing to sniff out discrepancies in expenditure data - what do you do when you have the information but don’t know if it contains signals about potential fraud and corruption related risk?

Here are some visualizations that some project teams built. A few photos from the event are here (thanks @neilfantom). More coming soon (and yes, videos too!). Thanks @francisgagnon for the first blog about the event. The event hashtag was #data4good (follow @datakind and @WBopenfinances for more updates on Twitter).

For those that missed the announcements earlier, the goal of the dive was fairly straightforward - explore practical and tangible ways to demonstrate that open/big data can help improve poverty measurement, and separately, improve how organizations such as the Bank tackle fraud and anti-corruption in projects. Ambitious ideas but leavened by a very action-first approach - it seemed to have worked out okay.

Our thanks to the volunteers, to the ambassadors from DataKind who organized this event with us, and to the World Bank experts who helped shape the project. Special thanks also to our partners at UNDP, UNDB, QCRI, and Global Pulse for their generous ‘data philanthropy’ during the event and for showing up and sharing your expertise with the participants. Thanks also to all the ‘speakers’ - Bertrand Badre, the new CFO of the World Bank Group and Chuck McDonough, VP and Controller, World Bank kicked off the event Friday, along with Patrick Meier (QCRI), Anoush Tatevossian (Global Pulse), Dafina Gercheva (UNDP), Wolfgang Fengler, Neil Fantom, Nobuo Yoshida, and Simon Robertson. Jane Campbell, Steven Zimmerman, and Peter Lanjaow were our ‘closers’. Thank you.

And Jake Porway and Julia Bezgacheva, of course. As also Giulio Quaggiotto, one of the moving forces behind the project.

A final shout out to the entire World Bank Finances team that organized the event, along with DataKind.

For those interested in the work that preceded the event, here go a few links --

Can big data help deliver better operational results
What happens when big data theory meets practice
Would you give up your personal data for development