Early Intervention Systems: Predicting Adverse Interactions Between Police and the Public. (March 2018)

• Record Type: Journal Article
• Authors: Helsby, Jennifer; Carton, Samuel; Joseph, Kenneth; Mahmud, Ayesha; Park, Youngsoo; Navarrete, Andrea; Ackermann, Klaus; Walsh, Joe; Haynes, Lauren; Cody, Crystal; Patterson, Major Estella; Ghani, Rayid
• Other Names: Stageman Daniel L. guest-editor.; Napolitano Nicole M. guest-editor.; Buchner Brian guest-editor.
• Is Part Of: Criminal justice policy review. Volume 29:Number 2(2018)
• Page Start: 190
• Page End: 209
• Publication Date: 2018-03
• Subjects: prediction -- machine learning -- early intervention system; Criminal justice, Administration of -- United States -- Periodicals; 364.973
• DOI: 10.1177/0887403417695380
• Languages: English
• ISSNs: 0887-4034

Abstract

Adverse interactions between police and the public hurt police legitimacy, cause harm to both officers and the public, and result in costly litigation. Early intervention systems (EISs) that flag officers considered most likely to be involved in one of these adverse events are an important tool for police supervision and for targeting interventions such as counseling or training. However, the EISs that exist are not data-driven and based on supervisor intuition. We have developed a data-driven EIS that uses a diverse set of data sources from the Charlotte-Mecklenburg Police Department and machine learning techniques to more accurately predict the officers who will have an adverse event. Our approach is able to significantly improve accuracy compared with their existing EIS: Preliminary results indicate a 20% reduction in false positives and a 75% increase in true positives.