Charleston Tests Predictive Analytics For Crime PreventionPolice department will use IBM software to detect robbery patterns and deploy officers to trouble spots.
Military Transformers: 20 Innovative Defense Technologies
(click image for larger view and for slideshow)
The police department of Charleston, S.C., is testing predictive analytics software from IBM as a way of predetermining where robberies and other crimes are likely to occur, then dispatching officers to those locations as a preventative measure.
The city's police department already uses a crime analysis system, holds weekly meetings to identify hot spots of activity, and has invested in technology to improve the "situational awareness" of its force. The predictive analysis software will take those efforts a step further by analyzing past and present crime records and evaluating incident and arrest patterns around the city.
Predictive analytics work for crime prevention, in theory, because crimes such as burglaries tend to occur in patterns--such as a cluster in the same neighborhood or during a certain time period. The goal of the pilot program is to station more officers where crimes are likely to occur.
The kind of information used in a crime-fighting predictive analytics system include the types of criminal offenses that are trending, time of day, day of week, and weather conditions. While the Charleston Police Department's pilot program is focused on robberies, the department hopes to expand the program to address other types of crime. Charleston PD is using IBM's SPSS predictive analytics technology in the pilot program; it already uses IBM's i2 Coplink technology for law enforcement.
Other cities using IBM's predictive analytics for crime prevention include Las Vegas, Memphis, and Rochester, Minn. In 2010, Memphis attributed a 31% decline in serious crime over several years largely to its "Blue Crush" preventative analytics system.
At the Big Data Analytics interactive InformationWeek Virtual Event, experts and solution providers will offer detailed insight into how to put big data to use in ad hoc analyses, what-if scenario planning, customer sentiment analysis, and the building of highly accurate data models to drive better predictions about fraud, risk, and customer behavior. It happens June 28.