Memphis Cracks Crime Trends With Forecasting Technology

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.