When a syringe-wielding drill thief tried sticking up a Home Depot near Yankee Stadium, police figured out quickly that it wasn’t a one-off. A man had also used a syringe a few weeks earlier while stealing a drill at another Home Depot 7 miles (11 kilometers) south in Manhattan.
The match, though, wasn’t made by an officer looking through files. It was done by pattern-recognition computer software developed by the New York Police Department.
The software, dubbed Patternizr, allows crime analysts stationed in each of the department’s 77 precincts to compare robberies, larcenies and thefts to hundreds of thousands of crimes logged in the NYPD’s database, transforming their hunt for crime patterns with the click of a button.
It’s much faster than the old method, which involved analysts sifting through reports, racking their brains for key details about various crimes and deciding whether they fit into a pattern. It’s more comprehensive, too, with analysts able to spot patterns across the city instead of just in their precinct.
“Because Patternizr picked up those key details in the algorithm, it brought back complaints from other precincts that I wouldn’t have known,” said Bronx crime analyst Rebecca Shutt, who worked on the Home Depot case. “That was incredibly helpful. That could have been a pattern that wasn’t made.”
The software also found two other thefts committed with a syringe by the same suspect, who was eventually arrested and pleaded guilty to larceny and assault.
Evan Levine, the NYPD’s assistant commissioner of data analytics, and Alex Chohlas-Wood, the department’s former director of analytics, spent two years developing the software before rolling it out in December 2016.
The department disclosed its use of the technology only this month, with Levine and Chohlas-Wood detailing their work in the INFORMS Journal on Applied Analytics in an article alerting other departments how they could create similar software. Speaking about it with the news media for the first time, they told The Associated Press recently that theirs is the first police department in the country to use a pattern-recognition tool like this.
“The goal of Patternizr is, of course, to improve public safety,” said Levine, an astrophysicist by academic training. “The more easily that we can identify patterns in those crimes, the more quickly we can identify and apprehend perpetrators.”
Levine and Chohlas-Wood were inspired by the work of a New York University team that studied a similar approach to pattern recognition but never produced a workable version.