The New York City Police Department is using a new software system called Patternizer, which helps officers search "hundreds of thousands" of case files, according to a report in The Washington Post .
The report says that the software was developed internally and allows analysts to search a wide range of files to look for patterns or similar crimes. Previously, they would have had to go through physical files. In one example, officers used the system to link two crimes: a man who used a syringe to steal a mock at two different Home Depots in New York City. Rebecca Shutt, the crime analyst who resolved the case, explained to Post that the system "brought back complaints from other precincts that I did not know."
This is not a Minority Report- as a system that seeks to predict where crimes will occur, nor is it a system that uses AI to analyze CCTV images. Rather, it is a system that searches for patterns in the New York police databases, allowing detectives to search a much wider data set in the course of an investigation. The system can help bring in additional sources of information from all of the NYPD, making it difficult to see patterns of crimes that could have occurred elsewhere.
The New York Police Department says the department released the software in 2016, but first revealed its existence in a number of INFORMS Journal on Applied Analytics . According to New York Police assistant data analysis commissioner Evan Levine and former analysis director Alex Chohlas-Wood, the department spent two years developing the software, claiming that the NYPD is the first in use a system of this type in the USA UU
Chohlas-Wood and Levine tell Post that they used 10 years of previously identified patterns to train the system, and in the tests, "they accurately recreated the patterns of ancient crimes by a third of the time. time "and returned parts of patterns 80 percent of the time." The Post says that the system does not consider the race of a suspect in the course of its search, as a precaution against racial prejudice.
The result seems to be one that helps to reduce some of the work that is required for researchers, partially automating a process that has been done manually until now.