Skip to content
Apply
Stories

Predictive policing software terrible at predicting crimes

People in this story

Wired, October 2023

Crime predictions generated for the police department in Plainfield, New Jersey, rarely lined up with reported crimes, an analysis by The Markup has found, adding new context to the debate over the efficacy of crime prediction software. Geolitica, known as PredPol until a 2021 rebrand, produces software that ingests data from crime incident reports and produces daily predictions on where and when crimes are most likely to occur.

We examined 23,631 predictions generated by Geolitica between February 25 and December 18, 2018, for the Plainfield Police Department (PD). Each prediction we analyzed from the company’s algorithm indicated that one type of crime was likely to occur in a location not patrolled by Plainfield PD. In the end, the success rate was less than half a percent. Fewer than 100 of the predictions lined up with a crime in the predicted category, that was also later reported to police.

Diving deeper, we looked at predictions specifically for robberies or aggravated assaults that were likely to occur in Plainfield and found a similarly low success rate: 0.6 percent. The pattern was even worse when we looked at burglary predictions, which had a success rate of 0.1 percent.

Continue reading at Wired.

More Stories

In this 2008 file photo, engineer Stephan Noetzel alerts a police officer to gunshots using ShotSpotter in East Palo Alto, Calif. Police and public officials nationwide continue to debate use of the technology.

13 Mass. municipalities and 1 university use ShotSpotter. Critics wonder: Is it worth it?

05.22.2024
Israeli Prime Minister Benjamin Netanyahu photographed during a press conference.

European leaders divided on ICC arrest warrant bid for Netanyahu

05.21.2024

Putin Showcases His Ambitions in a Chinese City Built by Czarist Russia

05.24.24
All Stories