Early Intervention System for Adverse Police Interactions

Fellows: Samuel Carton, Kenneth Joseph, Ayesha Mahmud, Youngsoo Park
Mentor: Joe Walsh
Project Partner: The White House and Charlotte-Mecklenburg Police Department
[Project Blog Post] [Paper]

This project is being continued at the Center for Data Science & Public Policy at the University of Chicago. For recent updates, results, and news, please visit the project web page.

Many police departments in the United States have developed and deployed “early warning systems” to identify officers who may benefit from additional training, resources, or counseling. These systems attempt to determine behavioral patterns that predict a higher risk of future adverse incidents, such as excessive use of force or citizen complaints. Detecting these actions opens new opportunities to develop targeted interventions for officers to protect their safety and improve police/community interactions.

As part of the White House Police Data Initiative, DSSG will partner with multiple police departments, including the Charlotte-Mecklenburg Police Department, applying data analysis to identify which factors should be used in early warning systems to flag at-risk officers before an adverse interaction occurs. Using anonymized police data, as well as contextual data about local crime and demographics, this model will detect the factors most indicative of future problems, so that departments can provide additional support to their officers. DSSG will analyze initial datasets this summer, and will scale up the research with additional police departments in the fall to build a viable prototype early warning system.