PITTSBURGH — New technology for analyzing more than a decade of extensive crime data may soon help police predict crimes in a given neighborhood one month in advance.
Researchers at Carnegie Mellon University say their software, to be released later this summer, can predict the number and types of crimes within a 10-block area with a 20 percent error rate.
"This is the next generation of crime mapping," said Wilpen Gorr, a Carnegie Mellon professor of public policy and management information systems.
A small team of researchers are running final tests on the project, which is funded by the National Institute of Justice.
With models similar to those economists use to warn of recession or inflation, Gorr said researchers matched criminal reports, 911 calls on shots fired and census data along with a mishmash of yellow page listings and seasonal variations.
Using crime data from Pittsburgh and Rochester, N.Y., collected from 1990 to 2001, researchers successfully predicted the number of burglaries, arsons, aggravated assaults, car thefts and other crimes. Murder and some other major crimes were not included because they are scarcer, Gorr said.
Although most officers on the beat have a general idea of what crimes to expect, any advances in mapping technology would be welcome, said Philip McGuire, assistant commissioner of programs and policies for the New York Police Department.
"If it's a more accepted position because it's science, not the gut feeling of a street officer, that is going to be heard by people making decisions for the department," McGuire said.