An Overview of the Philadelphia Predictive Policing Experiment

• In Event: Crime and Place: Philadelphia Predictive Policing Experiment: An Update

Abstract

The Philadelphia Predictive Policing Experiment is an ongoing collaboration between Temple University and the Philadelphia Police Department (PPD). This NIJ-funded research project represents the first place-based, randomized controlled experiment to study the impact of different police strategies on violent and property crime in predicted criminal activity areas. Predictive policing is an emerging tactic relying in part on software predicting the likely locations of criminal events. At present the law enforcement field lacks robust evidence to suggest the appropriate policing tactic in predicted areas. The research team from Temple University and the Research and Analysis section of the police department randomly assigned 20 PPD districts into one of four experimental conditions. Five districts acted as controls, in five districts officers were made aware of the predicted high crime activity area at roll call, in five districts an additional patrol car was dedicated to the predicted crime areas, and in five districts an unmarked unit was dedicated. Fieldwork ran for six months ending in early 2016. This presentation provides a detailed summary of the experiment. 

Author

• Jerry Ratcliffe, Temple University