The era of predicting and preventing “future crime,” a concept popularized in the film “Minority Report,” is upon us.
A new collaboration between a University of California Riverside sociologist and the Indio, California, Police Department uses historical data to predict where burglaries are most likely to occur. In other words, they built a computer model that tells the police department where crime is probably going to happen.
In the first nine months of 2013, the Indio police department actually dispatched police according to the computer model’s predictions of where thefts would occur by census block. Observers think that the program worked: Burglaries are 8 percent lower so far this year compared to the same time period last year.
Professor Robert Nash Parker and Indio Police Chief Richard P. Twiss used 10 years of police department data and records to to inform the computer model.
The most interesting finding from the project is the connection between truancy and burglaries.
“This is still cutting-edge and experimental,” Parker told the website Phys.org. “Big data gives you statistical power to make these kinds of predictions. It makes it possible for us to anticipate crime patterns, especially hot spots of crime, which allows law enforcement agencies to engage in targeted prevention activities that could disrupt the cause of crime before the crime happens.”
“We are deploying people differently and doing more community outreach,” Chief Twiss told Phys.org. “We discuss in briefing those areas that are being impacted. We had our crime analyst put maps together a few months ago based on trends we were seeing and we did pro-active patrols in those areas. Instead of having to respond to past crimes our arrests went up and instances of theft were reduced. We want to produce real-time, weekly hotspot maps that will predict patterns and trends. That’s the direction we’re heading.”