Predictive policing, or crime forecasting, is the application of analytical techniques—particularly quantitative methods—to identify targets for police intervention, prevent crime, or solve past crimes by making statistical predictions. Predictive policing can be divided into four broad categories containing methods for predicting crimes, offenders, suspects, and victims.

For the predictive focus within each broad category, conventional crime analysis (low to moderate data demand and complexity) and predictive analytics (large data demand and high complexity) can be distinguished. In designing police interventions based on predictive analysis, this comprehensive business process involves a four-step cycle. The first two steps entail collecting and analyzing crime, incident, and offender data to develop predictions. The third step consists of conducting police operations that intervene to prevent predicted threats to public safety. The fourth step involves the implementation of interventions. This includes rapid assessment that determines whether or not the implementation faithfully follows the intervention’s design, as well as the impact of the intervention based on relevant data collection and analysis.

This study addresses predictive policing myths and pitfalls. Recommendations address police agencies, predictive tools, and officers who implement interventions based on predictive analysis. The project developed a reference guide for law enforcement agencies interested in predictive policing that assesses the most promising technical tools for making predictions and the most promising tactical approaches for acting on predictions.

Additional information can be found at Office of Justice Programs, National Criminal Justice Service, https://www.ncjrs.gov/App/Publications/Abstract.aspx?ID=265907, September 2013, NCJ 243830.