A computer model created by scientists can foretell impending criminal activity up to a week in advance. The University of Chicago’s data scientists and social scientists have created an algorithm that uses open data to forecast upcoming violent and property crimes with a 90% accuracy rate. The socioeconomic class of the neighbourhoods where the crimes were reported significantly influenced how the police responded to these crimes, the researchers found using a different model.
“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
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.
Read more about this at gadgets360.com