Predictive Policing

On this page find:

Overview of Predictive Policing

Law enforcement work is frequently reactive: Officers respond to calls for service, quell disturbances and make arrests. Today more than ever, law enforcement work is also proactive.

In proactive policing, law enforcement uses data and analyzes patterns to understand the nature of a problem. Officers devise strategies and tactics to prevent or mitigate future harm. They evaluate results and revise practices to improve policing. Departments may combine an array of data with street intelligence and crime analysis to produce better assessments about what might happen next if they take various actions.

What Is Predictive Policing?
Predictive policing tries to harness the power of information, geospatial technologies and evidence-based intervention models to reduce crime and improve public safety. This two-pronged approach — applying advanced analytics to various data sets, in conjunction with intervention models — can move law enforcement from reacting to crimes into the realm of predicting what and where something is likely to happen and deploying resources accordingly.

The predictive policing approach does not replace traditional policing. Instead, it enhances existing approaches such as problem-oriented policing, community policing, intelligence-led policing and hot spot policing.

Predictive policing leverages computer models — such as those used in the business industry to anticipate how market conditions or industry trends will evolve over time — for law enforcement purposes, namely anticipating likely crime events and informing actions to prevent crime. Predictions can focus on variables such as places, people, groups or incidents. Demographic trends, parolee populations and economic conditions may all affect crime rates in particular areas. Using models supported by prior crime and environmental data to inform different kinds of interventions can help police reduce the number of crime incidents.

Research on Predictive Policing

Through a competitive process, NIJ has awarded grants to several agencies to conduct predictive policing research.

  • Demonstration and Evaluation Grants. NIJ awarded grants to law enforcement agencies to develop (Phase 1) and implement (Phase 2) predictive policing models. NIJ also awarded a grant to RAND to provide technical assistance to the agencies (Phase 1) and conduct an independent evaluation of the programs in practice to determine the efficacy of predictive policing (Phase 2).
  • Geospatial Police Strategies. NIJ has awarded grants to a number of institutions to conduct studies on using geospatial strategies to improve policing.

Learn more about NIJ's predictive policing and geospatial police strategies research.

Other Predictive Policing Activities

Predictive Policing Symposium. NIJ has convened two symposiums where researchers, practitioners and law enforcement leaders discussed predictive policing and its impact on crime and justice.
The first was held in Los Angeles, Calif., and focused on the concept of predictive policing. The symposium introduced a proposed initial working definition of predictive policing: “any policing strategy or tactic that develops and uses information and advanced analysis to inform forward-thinking crime prevention.” Read more about the definition.
The second symposium was held in Providence, R.I., and focused on how to make predictive policing available to all law enforcement agencies.

Read summaries of sessions from the two Predictive Policing Symposiums.

Predictive Policing Concept Mapping. NIJ held a concept mapping session at which researchers, practitioners and law enforcement leaders discussed existing and new ideas in the area of predictive policing. This concept mapping session was held on the final day of the 2010 NIJ Conference in Arlington, Va.

Predictive Policing: The Role of Crime Forecasting in Law Enforcement Operations. With funding from NIJ, RAND Corporation developed this reference guide for law enforcement agencies interested in predictive policing. The guide assesses the most promising technical tools for making predictions as well as the most promising tactical approaches for acting on predictions.

Learn more and download the report.

Date modified: June 9, 2014