The Philadelphia predictive policing experiment

• NCJ Number: 303062
• Journal: Journal of Experimental Criminology Dated: 2020
• Date Published: 2020
• Author(s): J. H. Ratcliffe; et al
• Grant Number(s): 2014-R2-CX-0002
• Agencies: NIJ-Sponsored
• Publication Type: Program/Project Evaluation

Annotation

This Philadelphia place-based, randomized experiment explored the impact of different patrol strategies on violent and property crime in microscale predicted crime areas.

Abstract

The experiment sought to determine whether different but operationally realistic police responses to crime forecasts estimated by a predictive policing software program could reduce crime. Twenty Philadelphia city districts were randomized to three interventions and one control condition. The three interventions comprised awareness districts (where officers were made aware of predicted areas on roll-call); marked car districts (where a marked patrol police car was dedicated to treatment areas); and unmarked car districts (a plain-clothes vehicle was dedicated to treatment areas). A business-as-usual approach represented the control condition in districts where staff had no access to the predictive software program. Two distinct 3-month phases examined crime outcomes for property and violent crime, respectively. The marked car treatment showed substantial benefits for property crime (31-percent reduction in expected crime count), as well as temporal diffusion of benefits to the subsequent 8-h period (40-percent reduction in expected crime count). No other intervention demonstrated meaningful crime reduction. These reductions were probably not sufficiently substantial to impact city or district-wide property crime. Some violent-crime results were contrary to expectations, but this happened in a context of extremely low crime counts in predicted areas. The small grid size areas hampered achieving statistical power. The experiment found reductions in property crime resulting from the marked car focused patrols. It also demonstrated the real-world challenges of estimating and preventing crime in small areas. (publisher abstract modified)