On this week’s TechKnow, Crystal Dilworth treks to Santa Cruz, Calif., and Seattle to investigate how their police departments are utilizing predictive policing software to anticipate crimes before they are committed.
The Santa Cruz Police Department began using the Predictive Policing (or PredPol) system as a way to pinpoint hot spots for automotive thefts, but soon realized that it could be useful in many other capacities.
“We found that the model was just incredibly accurate at predicting the times and locations where these crimes were likely to occur,” says Deputy Chief Steve Clark. “At that point, we realized we’ve got something here.”
“We’re not telling you how to do police work,” Clark reiterates. “We’re just telling you where the best locations are for you to be at any given time of the day.”
The Predictive Policing software is location-based, meaning that it does not profile criminals, but instead crunches statistics from past reported crimes to find areas where crimes are most likely to happen.
“All the computer takes into effect are actual incidents that have occurred and have been reported,” Clark explains. “It really doesn’t know anything about the demographics of individuals that live in that area, what the economic statuses of these individuals are, or anything about the person. It’s all area-specific.”
PredPol creates live maps in the police station that display past crimes as well as predicted hotspots, so officers know which areas to patrol more closely during their shifts. The software doesn’t account for a “gut instinct” when it comes to police work, but it can be a helpful tool to point cops in the right direction.