Scientists have developed a computer model capable of predicting crime that is about to occur up to a week before it takes place. Data scientists and social scientists at the University of Chicago have developed an algorithm that relies on public data to predict future violent and property crimes with 90 percent accuracy. Using a separate model, the researchers were also able to determine that there is a heavy bias in police response to these crimes, based on the socioeconomic status of neighbourhoods where the crime was reported.
“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 Ishanu Chattopadhyay, PhD, Assistant Professor of Medicine at the University of Chicago and senior author of the research paper.
The model was built and validated using historical data about crimes like homicides, assaults, batteries, burglaries, thefts, and motor vehicle thefts, as these crimes are the most likely to be reported to the police and are less prone to enforcement bias.
The new model allowed the researchers to discover specific patterns that were not seen using previous models that relied on “hotspots” of crime. These new insights allow the model to make more accurate predictions about future crime while at the same time allowing researchers to get a fresh view of neighbourhoods in the context of crime and police action. At the same time, researchers are quick to note that the data should not be used to direct police action for proactively preventing crime but as an additional tool to improve security in cities.
“We created a digital twin of urban environments. If you feed it data from what 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,” Chattopadhyay added saying that the model can be used as a simulation tool to see the different variables that may be affecting crime in the city.
