Afua Bruce


Afua joined DataKind from New America, where she was the Director of Engineering for the Public Interest Technology program. At New America, Afua oversaw projects in technology and policy to improve outcomes in criminal justice reform, foster care, immigration, the opioid epidemic, and more. She also supervised the Public Interest Technology University Network. Previously, she spent several years leading science and technology strategy and program management in the Federal government—as the Executive Director of the White House's National Science and Technology Council and in a variety of positions at the FBI. Prior to joining the Federal government, Afua started her career as a software engineer at IBM. Afua holds a degree in Computer Engineering from Purdue University, and an MBA from the University of Michigan.

14:25 - 14:50

Tuesday 11 May

Helping learners succeed: Improving University Success Through Predictive Modeling

According to a report by the National Student Clearinghouse, nearly half of all students entering college are at risk of leaving without earning a degree. John Jay College, located in New York City, inquired how existing student data and machine learning techniques could be combined to address challenges surrounding graduation completion rates. John Jay looked to DataKind to help answer these questions and develop a tool to support their efforts to improve graduation rates. Sponsored by the Mastercard Center for Inclusive Growth, with additional support from the Robin Hood Foundation, the DataKind team analyzed more than ten years of historical student data, identifying features associated with at risk students. The predictive model and insights were used to design effective interventions to reduce dropout, as well as a novel software application that allowed the John Jay administration to identify students at risk of drop out, so that the students can receive proactive outreach and support from the college. In its first year, the tool analyzed roughly 1,114 advanced credit students to identify students who were most at risk of stop-out or drop-out. Through targeted and strategic interventions, John Jay has already helped more than 800 of those students graduate over one year, or approximately 73%, compared to a projected graduation rate of 54% over two years for similar students without the tool and interventions. In support of this work, John Jay College received $800,000 for emergency grants and extra staff.