Law enforcement officers around the globe may be facing their toughest assignment yet—keeping crime rates down with fewer and fewer personnel and resources. This comes at a time when the worldwide economic crisis is likely to increase criminal activity. People take desperate measures in desperate times.
That’s why hundreds of police agencies around the globe are advancing crime-fighting techniques with an innovative 21st century approach. The growing use of predictive analytics technology is thwarting criminal activity by more precisely targeting investigations, deploying personnel and allocating limited resources, and ensuring the safety of officers.
With local policing budgets slashed 81% nationwide since 2001, according to the U.S. Conference of Mayors, local agencies are being asked to do more with existing resources.
Predictive analytics software plays a key role in helping law enforcement agencies successfully forecast criminal activities and deploy resources effectively in line with community expectations, while decreasing crime and improving public safety.
Colleen McCue is the senior research associate, security analytics at Innovative Analytics & Training LLC (IAT)
, a privately held company that specializes in expert and technical data sources. She said, “Law enforcement agencies face a daunting daily task—deciding where to most effectively deploy resources. Predictive analytics software has become integral to law enforcement agencies to easily uncover criminal patterns. It is as close to a crime crystal ball as we are ever going to get.”
By using predictive analytics—data mining, text mining, data collection, and statistical analysis—agencies worldwide are able to better understand and predict future criminal behavior by analyzing, modeling and scoring massive amounts of data—thousands of incident reports, crime tips, calls for service and criminal databases, as well as attitudinal data gathered through citizen feedback and surveys.
For police departments worldwide, this makes it easier to capture, predict, and act upon critical information and accelerate the criminal-investigation process, deploy officers where they are most needed, and identify minor crimes likely to escalate into violence. Capturing Citizen Feedback
Departments gain greater community support for law enforcement programs with predictive analytics feedback-management solutions. Analyzing attitudes, opinions and experiences from citizens is essential as it enables a police agency to better understand citizen needs or track important trends, such as an improving a community program.
Data collection solutions enable agencies to enrich understanding through community meetings and other methods with questionnaires that citizens can complete easily and cost effectively. Greater understanding enables an agency to align its priorities with those of the community. This not only increases cooperation in criminal investigations, but it leads to greater overall support for public safety and community outreach programs.
There are numerous methods to collect data about and from citizens: internal processes, in-person interviews, phone contacts, paper-based or online forms. Data-collection solutions help simplify and streamline the survey process. Because they are so flexible, these solutions also help a police agency increase response rates and get the results to decision makers that much faster.
The Greater Manchester Police (GMP) in Manchester, England, have a workforce of more than 7,000 police officers and 3,500 support staff. Serving about 2.5 million people and covering an area of 500 square miles and 10 metropolitan boroughs, it is one of the largest police forces in the United Kingdom.
Using data-collection software, GMP created questionnaires to gather a wide range of public views on area policing and where they needed improved programs. Successful completion of the survey project brought forward 400 people willing to work with the police force to deliver problem-solving initiatives in the relevant two wards—particularly relating to actions to stop youth offenses and anti-social behavior.
This solution has led to GMP to establish a community-based policing program that has reduced cost and time spent on survey research and analysis, as well as become a model organization for other police forces to follow.
Keith Bentley, the retired chief superintendent of operations at GMP, noted, “Not only did we benefit from a massive reduction in person time for this project, saving approximately €20,000 in two weeks, but these results are now being referenced by other Greater Manchester Police divisions as contributions to ‘efficiency savings’ required by government.”
Uncovering Patterns to Predict Crime
Law enforcement agencies are battling the exponential growth of data such as citizen feedback, criminal arrest records, and crime patterns, and the task at hand is to turn large and disparate volumes of data into actionable information. Predictive analytics data-mining software uncovers patterns in data using predictive techniques that play a critical role in decision making.
The predictability of violent crime is the foundation for behavioral analysis, as criminal behavior is repetitive. This enables the detection of anomalous, likely threatening pattern, which are key to detecting evolving threats.
By using predictive analytics, agencies are able to quickly analyze massive amounts of incident data such as 9-1-1 call transcripts—along with current and developing conditions, also known as “hot spots,” such as weather, time of day, city events or even paydays—to accurately predict criminal behavior patterns.
The Macon Police Department in Georgia works to create safe neighborhoods by reducing gun crime in alignment with the federal initiative, Project Safe Neighborhoods. Working with Applied Research Services, a national consulting firm specializing in criminal justice research, Macon has been able to identify the most violent and high-risk gun offenders.
Every time an offender is arrested or convicted of a crime, he is entered into a state’s Criminal History Records Repository. Applied Research Services is using predictive analytics to mine this data and identify a small group of offenders with extensive gun crime “careers.” The analysis provided from predictive analytics allows Macon to stay informed of new criminal activity among this group—allowing the criminal justice system to better focus law enforcement and prosecution resources on the most chronic and dangerous gun offenders.
Text mining is another component of predictive analytics that leverages critical insights locked in unstructured data, such as incident reports and witness.
The Netherlands Police Agency (KLPD) uses text-mining software to uncover hidden patterns and relationships in text. It developed its own Open Computer Forensic Architecture (OCFA), the “digital washing machine,” which creates an automated index out of the unstructured contents of a PC’s hard drive, enabling investigators to perform keyword searches for evidence.
Jochen van der Wal, technical engineer at KLPD, said, “After implementing text-mining software and deploying it to a crime case, we found an essential connection within just five minutes—which we couldn’t have found in the past three months of investigations. The combination of the OCFA framework and text analysis functionality to analyze huge amounts of evidence allows us to gain rapid insights in unstructured data.”
A Call to Action
Predictive analytics technology is used to capture a complete perspective such as citizen feedback, 9-1-1 call logs and also uncover patterns in data to predict crime—but what is this information worth if no one acts on the results?
The Richmond, VA Police use predictive analytics to predict and map crime. The officers understood that if criminal behavior follows an identifiable pattern (time, place, past histories, circumstances), they could use those factors that characterize the criminal act to predict its occurrence.
From this information, they’ve categorized violent crime types with a more granular approach to examine differentiating characteristics of violent (non-domestic) crime—robbery, burglary, auto theft, theft from auto, and all other larceny. As there are differing strategies and tactics to address each of these crimes, predictive analytics provides more intelligent analysis for precinct commanders.
Predictive analytics software has identified crime patterns for Richmond, and the agency is able to act on this information by deploying officers to potential hot spots, improving safety and protecting the lives of Richmond citizens. Using predictive analytics, the Richmond Police Department saw a 30% decrease in murder rates between 2006 and 2007 and a 20% decrease in rape.
The Memphis, TN Police Department (MPD) is proactively fighting crime with a data-driven approach. Officials use predictive analytics for enhanced crime analysis by mapping, identifying and linking precinct level and city-wide crime hot spots, such as outside of a concert, and crime trends, such as car burglary on rainy nights. In one specific hot spot, MPD has been able to reduce robberies by 80% by incorporating predictive analytics.
The MPD is analyzing crime patterns, trend maps, hot spot maps, and data on police call logs to identify and understand where clusters of robberies occur. By anticipating criminal activity, the organization is able to better deploy resources, including directed patrol, targeted traffic enforcement, task forces, operations, high visibility patrol and targeted investigations—all leading to crime reduction.
Larry Godwin, director of the MPD, said, “We are now able to better use our resources to address the needs of our citizens and more effectively fight crime. Predictive analytics software has also allowed the MPD to improve communication with policy makers and our citizens concerning crime in the city, our efforts to address it, our evolving needs to improve capacity, and the effectiveness of our efforts.”
Though criminals will try to be one step ahead of the law, police agencies deploying predictive analytics are able to maximize the effectiveness of their personnel and other resources, making our cities safer and keeping criminals at bay.
“This communication is enhanced because of our ability to provide information about specific crimes that are occurring in specific areas of the city on specific days of the week within a two-hour slice of time,” Godwin said. “In other words, predictive analytics allows MPD to direct resources at the most effective location on the most effective date at the most effective time.”
William (Bill) J. Haffey has been with SPSS Inc. since 1992 and is now the senior technical director for the company’s Public Sector division. He earned a bachelor’s degree in mathematics from The Ohio State University and a master’s degree in operations research from the Naval Postgraduate School, Monterey, CA.