Pattern Recognition Software helps cops to solve crime

nypd use pattern recognition

New software called Patternizr is being used by the New York City police to help them search through the endless number of case files. Developed by the department itself, the software is a boon to analysts to search across the hundreds of thousands of files for crimes with a similar pattern. Earlier, the cops would need to go through files physically.

This isn’t any AI based system, but it’s a system that conducts a thorough search through the complete database of NYPD. For instance, the system helped connect two crimes where a man who used a syringe to steal a drill in two different places in the city. The software helped to solve the case as it “brought back complaints from other precincts that I wouldn’t have known,” says Rebecca Shutt, the crime analyst solving the case.

Allowing the police force to a wider pool of data with additional sources of information will help in solving crimes in the city. Although rolled out in 2016, it was revealed just recently. The assistant commissioner of data analytics Evan Levine and the former director of analytics Alex Chohlas-Wood spent the past years developing the software.

The duo says that they used 10 years of previously-identified patterns to train the system and it has “accurately re-created old crime patterns one-third of the time and returned parts of patterns 80 percent of the time.”