A study on the algorithm titled "Event-level prediction of urban crime reveals a signature of enforcement bias in US cities" has been published in the journal Nature Human Behaviour.
Researchers from the University of Chicago (UChicago) created an algorithm that learned from temporal and geographic trends in historical data on violent and property crimes in the City of Chicago. The algorithm predicted future crimes up to a week ahead of time with approximately 90% accuracy. The algorithm was also tested with seven other US cities, performing similarly well.
"We created a digital twin of urban environments. If you feed it data from happened in the past, it will tell you what's going to happen in future. It's not magical, there are limitations, but we validated it and it works really well. Now you can use this as a simulation tool to see what happens if crime goes up in one area of the city, or there is increased enforcement in another area. If you apply all these different variables, you can see how the systems evolves in response," said Ishanu Chattopadhyay, Ph.D., Assistant Professor of Medicine at UChicago and senior author of the new study.
The model disregards conventional boundaries demarcated within the city, such as neighborhoods, and instead divides the city into evenly sized tiles about 1,000 feet (~305 meters) across, compared to previous attempts at crime prediction models. A separate model by the team also analyzed how police responded to crime, finding crimes in wealthier areas resulted in more arrests compared to fewer arrests for comparable criminal activity in poorer neighborhoods.
"What we're seeing is that when you stress the system, it requires more resources to arrest more people in response to crime in a wealthy area and draws police resources away from lower socioeconomic status areas," said Chattopadhyay.
You can read more from the study here.