Aug 24, 2017 | Atlanta, GA
Data Science for Social Good (DSSG) is an intensive, paid internship program where students are challenged to solve real-world problems for on-the-ground partners, including local non-profit organizations and the City of Atlanta. The annual student showcase was held at Ponce City Market on July 24th with representatives from the City of Atlanta, local companies, non-profit organizations, and data scientists in attendance. DSSG is a ten week program that blends the latest advances in the data sciences and technology design with partners who need to solve problems in the communities they serve. Seventeen interns were selected from a pool of over a hundred applicants from around the country. The students’ diverse backgrounds, in fields such as computer science, statistics, digital media, public policy, civil engineering, industrial engineering, and urban planning, were blended into multi-disciplinary teams and paired with an advising professor.
Brook Byers Institute of Sustainable Systems Fellow Bistra Dilkina advised one of the four student teams, with her team conducting two of the five projects in this latest round of the program. Dilkina is a Georgia Tech School of Computational Science and Engineering Assistant Professor and DSSG co-director, along with Ellen Zegura, who is the Stephen Fleming Chair of Telecommunications in the Georgia Tech School of Computer Science, and Christopher Le Dantec, who is an Assistant Professor in the School of Literature, Media, and Communication. Dilkina says of the program, “DSSG connects the classroom with real problems of deep community relevance. We hope this will inspire students to pursue their technical education further and to be engaged global citizens that use their education for societal impact.”
In the first project, Dilkina’s team of four students partnered with Georgia Tech Facilities Management to determine some useful predictors of energy usage beyond historical energy usage and performance modelling, such as class schedules and climatic variables. Facilities Management hopes to better model energy usage, inform operational planning, and identify upgrades and renovations that might not be commonly recommended, but will be most impactful. The second project Dilkina advised, entitled “Predicting and Alleviating Road Flooding in Senegal,” sought to learn which regions and roadways would be most affected by flooding, and where mitigations would best preserve capacity and access to all parts of the country. Coastal countries like Senegal are at increased risk of flooding as weather patterns become more erratic and sea levels rise. Students partnered with the United Nations Global Pulse, a big data humanitarian and development group inside the UN.
The other Data Science for Social Good projects for the 2017 round were:
Food for Thought: Analyzing Public Opinion on the Supplemental Nutrition Assistance Program
Cycle Atlanta: Seeing Like a Bike
Atlanta Housing Justice: The Anti-Displacement Tax Fund
In past years, Dilkina has led DSSG student teams working on diverse projects. In 2016, she partnered with local nonprofit New American Pathways to design a data-driven way to identify potential places for refugee resettlement in metro Atlanta. In 2015, she worked with the Atlanta Fire Rescue Department to build a predictive platform to help target commercial fire inspections, as well as with Trees Atlanta to efficiently identify tree planting locations and areas for forest preservation. In 2014, she led a team working with the City of Atlanta Emergency 911 Dispatch to inform new strategies for improving dispatchers’ workloads and overall response times to 911 calls.
The Atlanta chapter is part of a broader community of Data Science for Social Good programs that began at the University of Chicago in 2013. DSSG now has chapters at the University of Washington, the University of Massachusetts Amherst, and most recently at the IBM T.J. Watson Research Center. The emerging field of the data sciences is experiencing several growing pains, which the DSSG program serves to address: serving urgent communitty needs, developing the data science workforce by providing opportunities for students to gain experience, and helping students communicate effectively by working with real-world clients in a multi-disciplinary team structure. Students also learn critical skills such as stakeholder engagement, data acquisition and processing, data analysis and visualization, machine learning for predictive modeling, writing, and communicating results to nontechnical audiences.
Learn more about Design Science for Social Good here.