Skip to content
Apply
Stories

It Turns Out That Predictive Policing Software Is Pretty Terrible At Predicting Crimes

People in this story

A police car's front bumper faces forward.

Hackernoon, May 2025

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 Feb. 25 to Dec. 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.

Continue reading at Hackernoon.

More Stories

FILE - President Donald Trump, left, and Chinese President Xi Jinping, right, shake hands before their meeting at Gimhae International Airport in Busan, South Korea, Oct. 30, 2025. (AP Photo/Mark Schiefelbein, File)

What will Trump’s trip to China mean for the Iran war and the Strait of Hormuz?

05.14.2026

Boston’s budget crunch puts 1,800 afterschool jobs for young people on chopping block

05.13.2026

Why Americans are drinking less — and what it means for local bars

05.14.26
In the News