July 22, 2010 By Russell Nichols
Six years ago, the Memphis, Tenn., Police Department (MPD) decided to use technology to look into the future.
With the local crime rate soaring, software that could forecast where criminal activity would take place seemed like a promising idea, packed with potential. But crime analysts never predicted such explosive results.
Since 2006, with IBM predictive analytics technology, the MPD has reduced crime by 31 percent, including a reduction of 15.4 percent in violent crime, according to MPD officials.
In the days before the technology, the MPD -- like most police departments -- relied on human abilities to put offenses in spreadsheets and analyze trends the old-fashioned way, said John F. Williams, crime analysis unit manager with the MPD. In Memphis, those days are history.
"By putting the crime data on the map, we could concentrate on focus areas," Williams said. "The software spits out frequencies and cross tabs. We could see the base, the time of day, day of the week and the types of crimes, and we were able to deploy resources at the exact time the crimes were occurring. It blew our minds how accurate things were."
With predictive analytics, the MPD can evaluate incident patterns throughout the city and forecast criminal hot spots. The data allows the department to allocate resources to target areas and develop deployment strategies, including directed patrol, targeted traffic enforcement, task forces, operations, high-visibility patrol and targeted investigations.
In January 2010, for instance, targeted police operations in Memphis' Hollywood-Springdale neighborhood resulted in more than 50 arrests of drug dealers; the area has witnessed a 36.8 percent reduction in crime.
But, Williams added, the success of the predictive tool really comes down to diligent records management. To keep the crime data as close to real time as possible, crime analysts run data from the past 24 hours, the past 48 hours and the past 28 days consistently. That way, the colonel at each precinct can make mid-stream changes to the operations if necessary.
"Memphis Police Department now has the invaluable insight all of our staff can use --from the commanders to the patrolling officers -- to specifically focus investigative and patrol resources with the goal of preventing crime and making our neighborhoods safer," said Col. James Harvey, commander of the Ridgeway Station at the MPD.
To manage and compare crime data from years past, the MPD created Blue CRUSH (Criminal Reduction Utilizing Statistical History), built in partnership with the University of Memphis' Department of Criminology and Criminal Justice. Crime analysts plug the records from Blue CRUSH into the predictive tool.
"Once we put that information into the mapping software, you can see the crimes on the map," Williams said. "It is the responsibility of the crime analysts to look at what's happening and develop focus areas."
The technology not only enhances crime-fighting techniques, Williams said, but also improves collaboration. The crime analysts, for example, used to work divided among the city's nine precincts. Now, they work together in MPD's Real Time Crime Center (RTCC), a $3 million crime monitoring and analysis hub that opened in June 2008.
MPD reports an 863 percent return on investment in just 2.7 months, an average annual benefit of $7.2 million. Even with the recent reductions in crime, policing efforts remain ongoing. Each Thursday morning, the entire MPD command staff congregates to figure out if anything needs to change moving forward.
"We get together and go over this plan and see what works," Williams said, "and if something didn't work, [we discuss] what will we do in the upcoming week to make it work."
This Digital Communities white paper highlights discussions with IT officials in four counties that have adopted shared services models. Our aim was to learn about the obstacles these governments have faced when it comes to shared services and what it takes to overcome those roadblocks. We also spoke with several members of the IT industry who have thought long and hard about these issues. The paper offers some best practices for shared government-to-government services, but also points out challenges that government and industry still must overcome before this model gains widespread adoption.