Predicting crime with big data, affordably

Leslie Kennedy and Joel Caplan of Rutgers invented a technique that uses crime data to identify and map environmental attractors of crime. Called Risk Terrain Modeling (RTM), the spatial risk analysis technique takes crime data for a specific locale along with other data about the physical environment and forecasts where new crime incidents are likely to emerge and cluster. That information helps law enforcement agencies strategically allocate resources.

To make RTM more accessible to public safety professionals, Rutgers' School of Criminal Justice developed the Risk Terrain Modeling Diagnostics Utility, a software app that automates the steps of RTM. The product is bundled with affordable training or provided at no cost to practitioners who use it to diagnose spatial crime vulnerabilities and predict new crime locations. RTM is currently used by hundreds of U.S. crime analysts. The RTMDx™ Utility will bring expert knowledge and advanced technology to thousands more public safety professionals without requiring a major investment in time or money.

"Crime hotspots tell you where to go, but not what to do when you get there," said Kennedy, University Professor of Criminal Justice and director of the Rutgers Center on Public Security. "As symptoms of risky places, mapping recent crime yields valuable information, but not the complete picture of a problem place. Our system lets police prioritize risky places before crimes emerge and thoughtfully implement risk-mitigation activities. It's crime forecasting with a focus on places, not people."

"Police officers have described the feeling of playing whack-a-mole," said Caplan, assistant professor of Criminal Justice and associate director of Rutgers' Center on Public Security. "They identify crime hotspots and deploy resources there to deter illegal activity, only to have it pop up somewhere else or return to the same place once police leave. Hotspots tend to be quite resilient, not because police aren't effective, but because the environments that make certain places suitable for crimes don't change much over time. They remain attractive illegal behavior settings, so illegal behavior returns."

Risk Terrain Modeling "paints a picture" of physical features within municipalities that are attractive for certain types of illegal behavior, and in doing so, allows police to assign probabilities of crime occurring at certain places where many risk factors coexist, such as the stereotypical dead-ended remote alleyway with poor lighting.

"Some areas are less cliché or obvious, but just as risky and likely to experience lots of crimes," Caplan said. RTM examines the features of places that contribute to crime concentration. The RTMDx Utility standardizes the process of RTM and makes it more accessible to public safety professionals in both large and small departments.

The National Institute of Justice recently awarded two grants, totaling nearly $1 million, to conduct RTM research in seven U.S. cities: Newark; New York City; Chicago; Arlington, Texas; Colorado Springs, Colo.; Glendale, Ariz.; and Kansas City, Mo. Researchers from Rutgers' School of Criminal Justice and John Jay College of Criminal Justice at the City University of New York are conducting the studies using the RTMDx Utility. The Rutgers software is currently being used in the top four U.S. markets: New York, Los Angeles, Chicago and Miami. It is being adopted by industry and law enforcement offices in many countries, such as Australia and Canada, and major foreign cities such as Paris and Milan.

Kennedy and Caplan will present RTM and the RTMDx Utility at the White House Office of Science and Technology Policy "Safety Datapalooza" Jan. 14.