Memphis Cuts Crime With Predictive Analytics

What started as an experimental predictive crime-prevention initiative in 2005 is now a proven program that's about to get a big boost with new data and new forms of analysis.

IBM announced on Wednesday that the Memphis Police Department (MPD) is enhancing a predictive-analytics-based "Blue CRUSH" (Criminal Reduction Utilizing Statistical History) program by adding public call data to the information it analyzes to thwart crime before it occurs.

Launched five years ago by the University of Memphis Department of Criminology and Criminal Justice, the Blue CRUSH program started with analysis of historical data on gun crimes committed in North Memphis. Using predictive analytics software from SPSS (which was acquired last year by IBM), the University modeled patterns of crime and shared the results with area law enforcement agencies.

"Of course we knew the areas that had a lot of gun-related crime, but [Blue CRUSH] analyses helped us see patterns of exactly when and where the incidents were occurring," said John Williams, Crime Analyst Unit Manager at MPD. With better insight, the department was able to send patrols to the right places at the right times, increasing arrest while also curbing incidents, Williams said.

Early successes with Blue CRUSH led MPD to partner with the University as well as county and federal law enforcement agencies in 2006, pooling data and sharing insights on crime patterns. Analyses gradually expanded citywide, and the system now works in tandem with an MPD Real Time Crime Center (RTCC) monitoring and analysis hub opened in 2008.

Each week, the last four weeks' worth of crime data is joined to spatial geographic information system data. Incidents are then plotted on digital map of the city within the RTCC that is updated and monitored around the clock. Blue CRUSH analyses of 28-day and seven-day statistics pinpoint crime hot spots, with details down to the day of the week and times of the day that are most active.

Blue CRUSH is credited as a primary driver of a 31% reduction in serious crime in Memphis since 2006, but Williams said MPD hopes to do better. Predictive analyses are currently based strictly on crime reports submitted by police officers. Not included are the more than two million emergency and non-emergency calls received from the public each year. MPD is now adding these call records to the Blue CRUSH analysis.

"There are some parts of town where we get reports of shots fired, gang members hanging out, or drug activity, but when we get there, the subjects are gone and there are no arrests," Williams explained.

Call-volume and call-pattern analyses will not only uncover hot spots that don't show up in arrest reports, it will help the department predict where it can put resources and change its approach to be more effective.

"If we can deploy some of our unmarked cars and undercover officers in these areas, we're going to make arrests," Williams said.