By Reading Crime Patterns The Algorithm Can Position Future Police Resources
In a clear case of life imitating art, we bring you the story of an algorithm that can predict the future. Of crime. And gets it right about 90% of the time. Matt Wood has written a piece for scitechdaily.com that has a familiar feel to it when it comes to fighting crime that has not happened yet.
University of Chicago data and social scientists have developed a new algorithm that forecasts crime by learning patterns in time and geographic locations from public data on violent and property crimes. It has successfully predicted future crimes one week in advance with approximately 90% accuracy.
The researchers also studied police response by analyzing the number of arrests following incidents and comparing those rates among neighborhoods with different socioeconomic statuses. Crime in wealthier areas resulted in more arrests; arrests in disadvantaged neighborhoods dropped. Since more crime in poor areas did not lead to more arrests, researchers cited bias in police response and enforcement.
“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 UChicago and senior author of the new study, which was published on June 30, 2022, in the journal Nature Human Behaviour.
Researchers tested this new tool by looking at information on two Chicago crime categories: Violent crime and property crime. And by reading the past, they say they can predict the future. Wait, where have we heard that before?
By mapping the patterns they are looking for in a grid on the city broken into 1,000-foot squares. And this algorithm appears to work equally well in eight other major American cities.
“We demonstrate the importance of discovering city-specific patterns for the prediction of reported crime, which generates a fresh view on neighborhoods in the city, allows us to ask novel questions, and lets us evaluate police action in new ways,” Evans said.
Researchers were careful to note that the tool’s accuracy does not mean that it should be used to direct law enforcement to target neighborhoods proactively for crime prevention. Instead, it should be added to policing strategies to address crime.
Another interesting point the research found, was that moving police resources to wealthier neighborhoods only depletes resources in the less affluent ones. And data shows wealthier neighborhood crimes usually end up in an arrest far more than in poorer areas.
read more at scitechdaily.com