The New York Police Department (NYPD) is solving crimes with help from pattern-recognition software, according to a number of reports.

Aptly named Patternizr, the software enables NYPD officers to comb through hundreds of thousands of database case files in search of possible crime patterns across the department’s 77 different precincts. Using 10 years of confirmed pattern data, the NYPD developed the software in-house over the course of two years. Although it has been employed by the NYPD since 2016, the software was only made public in a recent issue of Informs Journal on Applied Analytics.

Traditionally, NYPD officers sorted through physical case files in search of patterns, a process that was time-consuming and that could not easily work across precincts. However, during testing of the Patternizr software, researchers found that the software “accurately re-created old crime patterns one-third of the time and returned parts of patterns 80 percent of the time,” according to reports.

One example of the effectiveness of the software was demonstrated with the recent arrest of a syringe-wielding suspect who had allegedly stolen drills from two New York City Home Depots. According to Rebecca Shutt, a crime analyst who had solved the case using the software, the system noticed patterns in both crimes and notified law enforcement of the similarities of the two crimes, something that might not have happened before the software as not every precinct complaint is visible to other precincts.

“The real advantage of the tool is that we minimize the amount of leg work and busy work that analysts or detectives have to do, and really allow them to leverage their expertise and their experience in going through a much smaller list of results,” said Alex Chohlas-Wood, who developed the software along with Evan Levine, the NYPD assistant commissioner of data analytics.