Across policy domains, practitioners and researchers are benefiting from a trend of greater access to both more detailed and frequent data and the increased computing power needed to work with large, longitudinal data sets. There is growing interest in using such data as a case management tool, to better understand patterns of behavior, better manage caseload dynamics, and better target individuals for interventions. In particular, predictive analytics — which has long been used in business and marketing research — is gaining currency as a way for social service providers to identify individuals who are at risk of adverse outcomes. We model the experiences of individuals whose outcomes are known in order to predict outcomes for others.

MDRC has multiple predictive analytics efforts underway:
  • We use machine learning algorithms, which allow us to extract information from a large number of measures and thus capture wide-ranging risk factors.
  • We use ensemble learning, which allows us to compare multiple machine learning algorithms and other modeling approaches and select the best one based on its predictive performance in new samples.

In recent and ongoing researcher-practitioner partnerships with service providers, we are incorporating our predictive analytics approach into institutions’ caseload management systems and continuous improvement processes.

We work in close partnership with service providers because it is critical not just for maximizing the usefulness of the analysis but also for maximizing the accuracy of predictions

We also study the implementation and use of existing, validated predictive analytics tools. Lessons learned from the actual adoption of tools can provide valuable information for methodological consideration.

Read the full article on using predictive analytics by Kristin Porter, Rekha Balu and Richard Hendra at MDRC