Free Shipping on orders over US$39.99 How to make these links

A computer algorithm can predict crime in US cities a week before it happens


(Bloomberg)-A new computer algorithm can now predict crime in a major city near you.

The algorithm, developed by social scientists at the University of Chicago and expressed with 90% accuracy, divides towns into 1,000-square-foot tiles, according to a study published in Nature Human Behavior. The researchers used historical data on violent crimes and property crimes from Chicago to test the model, noting patterns over time in these tiled areas trying to predict future events. It also works using data from other major cities, including Atlanta, Los Angeles and Philadelphia, the study showed.

The new tool contrasts with previous models for prediction, describing crime that has arisen from “hotspots” that have spread to surrounding areas. Such an approach is likely to eliminate the complex social environment of towns, as well as the nuanced relationship between crime and the effects of police enforcement, thus leaving room for discrimination, according to the report.

“It’s hard to argue without bias when people sit down and figure out what patterns they’re looking at to predict crime because these patterns, in themselves, don’t mean anything,” he said. by Ishanu Chattopadhyay, Assistant Professor of Medicine at the University of Chicago and senior author of the study. “But now, you can ask complex algorithmic questions like: ‘What will happen to the violent crime rate if property crimes go up?’

Other crime prediction models previously used by law enforcement have been found to erroneously target certain people based on a narrower set of factors. In 2012, the Chicago Police Department – along with academic researchers – implemented the “Crime and Victim Risk Model” that compiled a list of so -called strategic topics, or potential victims and perpetrators. the number of shooting incidents determined by factors such as age and history of arrest. .

The model provides a score that determines how urgently people on the list should be monitored, and a higher score means they are more likely to be considered a potential victim or commit a gun crime.


But after a lengthy legal battle, a Chicago Sun-Times investigation revealed in 2017 that nearly half of the people the model identified as potential culprits had not yet been charged with illegal gun possession, while 13% have not yet been charged with a serious offense. In contrast, the tool designed by Chattopadhyay and his colleagues uses hundreds of thousands of sociological criteria to determine crime risk in a particular time and space.

The study, “The Level of Incidence Prediction of Urban Crime Reveals Signature of Enforcement Bias in U.S. Cities,” was supported by the Defense Advanced Research Projects Agency and the Neubauer Collegium for Culture and Society.

© 2022 Bloomberg LP



Source link

We will be happy to hear your thoughts

Leave a reply

Info Bbea
Logo
Enable registration in settings - general
Compare items
  • Total (0)
Compare
0
Shopping cart