Home Technology Study: Artificial intelligence can predict crime a week before it happens

Study: Artificial intelligence can predict crime a week before it happens


A team of researchers from the University of Chicago has created an artificial intelligence algorithm that can predict crimes up to a week in advance with up to 90% accuracy.

The researchers created a model using historical crime data to predict future events in a 1,000-square-foot area. The technology has been demonstrated in eight major US cities, including Chicago, Los Angeles, and Philadelphia.

Professor Ishanu said Chattopadhyay From the University of Chicago: “We have created a digital twin for the urban environment. If you give him data about what happened in the past, he will tell you what will happen in the future. It’s not magic, there are limitations, but we’ve tested it and it works very well.”

Professor Chattopadhyay adds that this tool reminds us of crime predictions made in the 2002 science fiction film Minority Report, which was itself based on a short story about the same anecdote written by Philip K. Dick in 1956.

Similar AI-based technology is already being used in Japan to inform citizens about patrol routes in some municipalities, where crimes are statistically more likely to occur in certain areas at certain times.

The various technology options have generated controversy, with a Crime and Victimization Risk Model implemented by the Chicago Police Department in 2012 found to be flawed due to the use of historically biased data.

These efforts also relied on a seismic approach, where crime is portrayed as originating in “hot spots” that spread to surrounding areas. In contrast, Chicago researchers have shaped the complex social environment of cities, as well as the relationship between crime and the effects of policing.

“Spatial models ignore the natural topology of the city,” said Max Palfskem, a professor of sociology at the University of Chicago who participated in the study.

“Transport networks take into account streets, lanes, trains and bus routes, as well as communication networks and domains with similar socioeconomic status. Our model allows us to detect these connections.”

Source: independent


Exit mobile version