Predictive Policing: Working the Odds to Prevent Future Crimes
Police in Santa Cruz, California, are using a computer program to predict where burglaries and other crimes might take place based on past events and forecasting, and using that information to deploy resources more smartly.
Crime is often a clustering event: if there is an act of inter-gang violence, for instance, there’s likely to be a retaliatory act shortly after. If there is a home burglary, there may be another burglary in the neighborhood or even the same home soon after.
It’s those details that are key to a Santa Cruz, California, experiment called predictive policing, an effort combining criminology, anthropology and mathematics to plan how to deploy police resources.
Here’s an example of how forecasting and directed patrols play out, from a New York Times story last month, “Sending the Police Before There’s a Crime”:
The arrests were routine. Two women were taken into custody after they were discovered peering into cars in a downtown parking garage in Santa Cruz, Calif. One woman was found to have outstanding warrants; the other was carrying illegal drugs.
But the presence of the police officers in the garage that Friday afternoon in July was anything but ordinary: They were directed to the parking structure by a computer program that had predicted that car burglaries were especially likely there that day.
“We’re facing a situation where we have 30 percent more calls for service but 20 percent less staff than in the year 2000, and that is going to continue to be our reality,” Zach Friend, the police department’s crime analyst, told the Times. “We have to deploy our resources in a more effective way, and we thought this model would help.”
Friend said the program has led to five arrests and the pre-emption of several crimes since it launched in July.
As detailed in the Times, the modeling is based on models for predicting aftershocks from earthquakes and “generates projections about which areas and windows of time are at highest risk for future crimes by analyzing and detecting patterns in years of past crime data.” The model is recalibrated daily, with patrols adapting to whatever the model says the new highest risk areas are.
George Mohler of Santa Clara University is the mathematician on the project. According to Mohler’s website, the crime prediction software is licensed through the Stanford University Office of Technology Licensing.