Artificial intelligence scientists create a new tool that can predict crimes a week before they occur, with an accuracy of up to 90 percent.
The British Independent newspaper said researchers at the University of Chicago have created a tool that uses historical crime data to predict future events in an area of 1,000 square feet.
This technology has been used in eight major US cities, including Chicago and Los Angeles. Professor Ishanu Chattopadhyay of the University of Chicago said: “We have created a digital twin of urban environments. If you give it data from what happened in the past, it will tell you what will happen in the future…
It’s not magic, there are limitations, but we checked, and it works really well.” The tool is reminiscent of the crime predictions made in the 2002 science fiction film Minority Report, which itself was based on a portion of the same story written by Philip K.
Dick in 1956. Similar AI-based technology is already being used in Japan to assist patrols in some municipalities where crimes are statistically more likely to occur in certain areas and at specific times.
Differences related to technology have proven controversial, with the Crime and Abuse Risk Model implemented by the Chicago Police Department in 2012 found to be flawed due to the use of historically biased data. These efforts have also relied on a seismic approach, where crime is portrayed as originating in “hotspots” that spread to surrounding areas.
By contrast, researchers in Chicago have modeled the complex social environment of cities, as well as the relationship between crime and the effects of police action.
“Spatial models ignore the natural topology of the city,” said Max Palfskem, a professor of sociology at the University of Chicago who was involved in the research.
A detailed study of the latest research, titled “Event-level forecasting of urban crime reveals law enforcement bias in US cities,” was published in the scientific journal Nature Human Behavior on Thursday.