Research on Repeat Crime Risk Leads to Software Tool Development

• NCJ Number: 250548
• Date Published: January 2017
• Agencies: NIJ
• Publication Type: Research (Applied/Empirical), Report (Study/Research), Report (Grant Sponsored), Program/Project Description
• Grant Number(s): 2010-DE-BX-K004
• Award: Predictive modeling combining short and long-term crime risk potential

Annotation

This web page profiles and provides free downloading access to the beta version of a software tool that enables law enforcement agencies to forecast the risk for particular types of crime by geographic location.

Abstract

The acronym for the software is PROVE (Prediction of Repeat Offending and Victimization in the Environment), The research team that developed PROVE partnered with Azavea, a Philadelphia-based company that creates civic geospatial software and data analytics for the web. The research team examined Philadelphia statistics for crimes that included homicide, rape, aggravated assault, robbery, burglary, and motor vehicle theft. Researchers also considered long-term and short-term risk and near-repeat crimes on a 2-week timeframe. Their analysis determined that a model combining community structural characteristics, crime counts for the previous year, and an estimate of near-repeat activity produced the best results overall. It is emphasized that the tool predicts the potential risk of the type and place of a crime, not a specific person or persons likely to commit the crime. This report cautions, however, that PROVE is based on calculations generated by only Philadelphia data, so analysts should be cautious in applying results in other areas. The download link provided is for the beta test version for informational purposes. The final version is scheduled to be released later in 2017. It may differ significantly from the beta version due to changes made as a result of the beta test.