As part of the Bureau of Justice Assistance (BJA)-funded initiative Using Analytics to Improve Officer Safety, CNA’s Center for Justice Research and Innovation produced this bulletin as a companion document to an issue brief that provides an in-depth look into the use of predictive analytics in policing. Visit CNA’s Officer Safety and Wellness page to learn more about this initiative.
Predictive analytics in policing “is a data-driven approach to characterizing crime patterns across time and space and leveraging this knowledge for the prevention of crime and disorder.”1 Its use has evolved in the last several decades as a promising method to reduce and prevent crime. This bulletin provides information for law enforcement agencies and their stakeholders (e.g., crime analysts, policy makers, and researchers) interested in learning more about the role of predictive analytics in police operations.
PREDICTIVE ANALYTICS IN POLICING
HOT SPOT DETECTION
According to Selbst (2017),2 hot spot detection involves mapping crime locations to pinpoint geographically defined clusters of crime, known as “hot spots.” Hot spot detection moves agencies away from geographic‑based patrols or deployments and toward incident‑based patrols or deployments, allocating an agency’s resources to areas that most need or most request them.
RISK TERRAIN MODELING
Risk terrain modeling (RTM) starts with identifying “all factors that are related to a particular outcome for which risk is being assessed” and then “assigns a value signifying the presence, absence or intensity of each factor at every place throughout a given geography.” Each factor is represented by a separate map of the same geography, and the maps are combined to create the risk terrain map.
IDENTIFYING PREVENTION OPPORTUNITIES
Identifying prevention opportunities involves focusing resources on places and individuals that have been historically involved as drivers of crime. In some applications, a scoring method is created based on a number of factors including criminal history, address, and social media use.Download full report
This work was performed under BJA-2018-DP-BX-K015. This project was supported by Cooperative Agreement Number BJA‑2018‑DP‑BX-K015 awarded by the Bureau of Justice Assista, U.S. Department of Justice. The opinions contained herein are those of the author(s) and do not necessarily represent the official position or policies of the U.S. Department of Justice. References to specific agencies, companies, products, or services should not be considered an endorsement by the author(s) or the U.S. Department of Justice. Rather, the references are illustrations to supplement discussion of the issues.
- Document Number: IIM‑2021‑U‑030293
- Publication Date: 1/25/2022