Predicting Risk in Social Service and Education Programs
Social service and education programs aim to help the people they serve achieve positive outcomes (for example, completing a degree or getting a job). But some participants still don’t succeed. Could predicting who is more at risk of not meeting important milestones allow programs to intervene with supports for those who most need them?
Predictive analytics is a tool that can help programs use existing data to make predictions of risk for their clients. Program staff can identify milestones, which, if not met, can prompt action. For example, if a child is not reading at grade level by grade 3, school staff can provide additional supports to help avoid unwanted future outcomes, such as failing or dropping out.
Join Katie Beal as she talks to Rekha Balu, Director of MDRC’s Center for Applied Behavioral Science, who describes how predictive analytics is informing MDRC’s work, and to Brad Dudding, Chief Operating Officer at the Center for Employment Opportunities (CEO), who explains how CEO is using predictive analytics to help formerly incarcerated individuals gain employment and reduce recidivism.
About Evidence First
Policymakers talk about solutions, but which ones really work? MDRC’s Evidence First podcast features experts—program administrators, policymakers, and researchers—talking about the best evidence available on education and social programs that serve people with low incomes.
About Leigh Parise
Evidence First host Leigh Parise plays a lead role in MDRC’s education-focused program-development efforts and conducts mixed-methods education research. More
