The Department of Pre-Crime is intriguing conceptual material used in the 2002 science fiction film Minority Report, and it's inching toward reality for the Richmond, Va., Police Department. Instead of using the fictitious "precogs" who float in a pool of water while foreseeing crimes, the police department uses crime analysis and prediction.
The concept is based on the idea that criminal behavior follows identifiable patterns, more often than not, that can be used to predict criminal acts. By collecting previous crime statistics and external factors -- weather, time of day, day of week, moon phases, etc. -- officers can estimate when and where crimes might occur using business intelligence (BI) capabilities.
A new system was rolled out in a phased implementation beginning in 2006 that provides predictive crime analysis, data mining, reporting and GIS capabilities too the entire Richmond P.D. The result is that officers receive the most up-to-date information available, along with a screen of predictions of crime hot spots they can access before a shift. Data from the records management system is integrated and analyzed on a continuous basis.
The Richmond Police Department's innovative enterprise platform has produced dramatic results. By moving from a "reactive crisis management structure" to a "proactive problem deference model," the department lowered the city's ranking from 5th most dangerous U.S. city in 2004 to 15th most dangerous city in 2005, with a 21 percent reduction in major crime from 2005 to 2006. The department also won Gartner's 2007 BI Excellence Award.
"What we're doing is replicating the intuitive nature of the seasoned veteran cops, the guys that have been on the force for 25 years and know certain sections of city really well and operate almost out of complete intuition, who know more than a crime map might show them," said Stephen Hollifield, information services manager of the Richmond Police Department. "What our application attempts to do is the same thing, but provide that type of intuitive picture about areas and give them to our green officers who have been on the force for only two years and haven't developed that sense yet. This kind of speeds up the process and gives pictures based on all the crimes in the past, weather, times of day, day of week and moon phases."
Business Intelligence Approach Works
The Richmond Police began down the road of predicting crime in 2005, when the department named Rodney Monroe the new police chief of the department's 700 officers. With the immediate objective of lowering the city's crime rate for Richmond's 220,000 residents, Monroe met with BI software vendor Information Builders and analytical software vendor SPSS Inc. to see how technology could help.
At the time, the police department was data rich and information poor: A vast wealth of historical data was gleaned from its mature 911 system, computer-assisted dispatch and records management system, which all were used to track crime and ensure quality of service. Yet like many organizations, the police lacked a BI solution that could make use of the data.
Obviously data has become a valuable collected resource for numerous government organizations in recent years, but effective utilization of it -- through tools like BI -- has lagged behind. That's why BI has consistently ranked as a top priority for CIOs over the last few years, according to Gartner.
BI can offer an organization invaluable system analysis by collecting, analyzing and integrating data, while providing historical, current and predictive views of business operations. The integrated reporting and analysis allows managers to determine better management of an organization, improve services, identify effective strategies, enhance security and increase efficiency, among other things.
The first task for the Richmond Police was to identify data that would be used to create predictive crime reports -- factors that didn't have variables that could change drastically over short periods of time. This created a
model that automatically improves itself and avoids manual refreshing the variables. The chosen data included: time of day, day of week, holidays, weather, moon phases, city events, paydays and crime records. All the analyzed data was at least five years old to ensure the integrity of the predictions.
"While the model places higher emphasis on the more recent data, the five-year window lessens our odds of predicting based on anomalies in any one data source," Hollifield said.
Since there weren't any packaged solutions that provided what the Richmond Police required, it was forced to develop a custom solution with several different technologies. The police data was integrated with Information Builders' WebFOCUS software, with BI capabilities for analytics and reporting. The platform uses WebFOCUS as the primary user interface that displays criminal activity every four hours, which enables each new shift of officers to make adjustments for how they patrol. This information is available to officers at police stations and in squad cars; real-time alerts are sent through e-mail and text messages when extra officers need to be deployed.
GIS mapping and dynamic geographical displays from ESRI and aerial photography from Pictometry International provide detailed pictures and dynamic geographical displays of the reported incident's location and the surrounding neighborhoods. The department used SPSS's Clementine and Predictive Enterprise Services product for data mining capabilities that examine how current crime reports relate to data on past, present and projected actions.
The system was integrated with Richmond.com, which feeds it contextual information about local activities, such as sporting events and a city-maintained weather data collection system.
Crime Prevention Sophistication
The GIS capabilities allow officers to view specific types of crime for a given area and perform crime mapping and analysis functions. Officers can view maps of crime density hot spots by location or based on crime type, such as car theft, to see specific incidents within a ZIP code, neighborhood, city district or other user-defined area. Data for weather, events, time of day, case history, associated suspects and aerial photos can also be integrated. The end result is a sophisticated data model of criminal activity with a user-defined set of elements that predict future criminal behavior.
The platform significantly reduced incident rates of murder (32 percent), rape (20 percent), robbery (3 percent), aggravated assault (18 percent), burglary (18 percent) and auto theft (13 percent) from 2006 to 2007. A New Year's initiative used the platform to deploy officers in targeted areas, which resulted in a 49 percent reduction in random gunfire incidents and a 246 percent increase in weapons seized -- and only one-third as many officers were deployed as previous years, resulting in a $15,000 savings of overtime.
Analyses of criminal behavior also determined what crimes should be treated as a higher priority to prevent them in the future. For instance, certain property crimes were better indicators of likely sexual assaults than the presence of convicted sex offenders.
"Now instead of looking at their static data, [officers] pull BI reports every two weeks and see where crimes are taking place," said Jeff Vining, research vice president of Gartner, specializing in homeland security and law enforcement. "They wanted to be more predictive and have the officers there before a crime is committed; that's what makes this unique."
While metropolitan areas like Chicago, New York and Los Angeles use similar crime analysis with BI tools, the Richmond Police Department is unique because it found its own solution with a limited budget, Vining said.
Soon the Richmond Police Department will roll out the next phase of the application by moving from predicting all violent crime types in aggregate to a more granular approach that predicts the intensity of crime within four hour windows via seven- and 30-day forecasts. The system will categorize crimes by nondomestic, robbery, burglary, auto theft, theft from auto and all other larceny. With different strategies and tactics to address each type of crime, the new model will provide more intelligent analysis for Richmond's precinct commanders, Hollifield said.
"This is going to give us a prediction of what to expect over the next seven days and what to expect broken out in four hour windows," Hollifield said. "In that four hour window we can predict what particular crime type could occur and the probability of that crime happening."
Minority Report publicity photo Copyright ©2002 20th Century Fox and DreamWorks L.L.C. All Rights Reserved.
NEW ON THE PODCAST