The software, according to PredPol, was twice as good as human analysts at predicting where car break-ins and burglaries would occur. When patrol officers focused on the areas identified by the algorithm, those places say a 25 percent reduction in reported burglaries. Reporter David Talbot describes the process:
“The inputs are straightforward: previous crime reports, which include the time and location of a crime. The software is informed by sociological studies of criminal behavior, which include the insight that burglars often ply the same area.
“The system produces, for each patrol shift, printed maps speckled with red boxes, 500 feet on each side, suggesting where property crimes—specifically, burglaries and car break-ins and thefts—are statistically more likely to happen. Patterns detected over a period of several years—as well as recent clusters—figure in the algorithm, and the boxes are recalibrated for each patrol shift based on the timeliest data.”
It is difficult to definitively prove that the application is directly responsible for the reduced crime rate, though the team did all it could to make the case; the results of using the software’s reports compared favorably to those of human analysts’ recommendations and to randomly generated red boxes. At the very least, though, using the software reduces the time officers must spend planning their beats, so they can spend more time on the streets. That’s a good thing.
The fledgling company PredPol seeks to fill an important niche, helping police departments to be more successful even as they must cope with plunging budgets. The software sprang from computer science and anthropological research performed at Santa Clara University and the University of California, Los Angeles. The company is based in Santa Cruz.
This article was written by Cynthia Murrell, August 15, 2012 for ArnoldIT.com