Blue CRUSH: Fighting Crime With Predictive Policing


When we think about Memphis, Tennessee, traditionally we think about great music and fantastic barbecue. Now, we can add a third trait, which is an innovative and transformative way to fight crime. Larry Godwin, Director of Police Services, Memphis Police Department, recently was profiled in an IBM Smarter Planet Leadership Series Report, highlighting the “Blue CRUSH” (Criminal Reduction Utilizing Statistical History) program. GovLoop recently hosted a webinar, speaking with Dr. Janikowski, another key player in the development of the Blue CRUSH program.

Larry has a fascinating background that has led him to become the Director of Police Services in Memphis. Prior to his current role, Larry served as a U.S. Marine and has worked for the police department for the last 38 years. During his tenure, Larry has worked at nearly all levels at the department. The IBM report states, “After starting out undercover, Godwin went on to work in just about every part of the Memphis PD, including uniform patrol, SWAT, homicide and special operations, where he was Deputy Director before assuming his current job in 2004.”

The report is a fascinating read and sheds light into Godwin’s leadership style. Coming up through the ranks, Larry has a keen understanding of what it takes to fight crime effectively in Memphis. The IBM report identifies that during his tenure as Director of Police Services, he insisted on changing a uniform policy of the department. Previously, all officers in the field wore blue shirts, and all leaders on the force, wore white shirts. Larry changed this policy so that all members wore blue shirts, identifying that they are a team. This small change is an indication of a leadership style of collaboration, working as a team, and stark difference to the hierarchical model of thinking that is often found within police departments.

Larry states, “Nobody knows a ward better than the patrolman who rides as many as six or seven days a week for eight to ten hours a day. Showing our willingness to learn from their knowledge and experience is the best way to get them to take ownership.” This quote is further evidence of his leadership style focusing on collaboration, and also shows how Larry can relate to each member of the police department.

Under Larry’s direction, the Memphis Police Department has started to try and tackle crime through innovative strategies, predominantly focusing on predictive crime prevention practices. Larry called together colleagues and began to explain the dire situation facing the police department. As with many local governments, Memphis faced shrinking budgets, disillusioned citizens, and was challenged to think of new ways to curb trends of rising crime.

With Larry setting the stage and explaining the situation facing the city, representatives from the Organized Crime Unite, District Attorney General Bill Gibbons, and Dr. Richard Janikowski, a professor of Criminology at the University of Memphis, started to think through innovative solutions to curtail rising crime in a time of fiscal austerity.


Professor Janikowski had worked on a variety of analytical initiatives to understand crime data. At the University of Memphis, Professor Janikowski also served as the Director of the Center for Community Criminology and Research. The IBM report states, “Now, with the MPD requesting his input, Janikowski saw the opportunity to put into practice the simple yet powerful principle that “If you focus police resources intelligently by putting them in the right place, on the right day, at the right time—good things are going to happen,” says Janikowski. “You’ll either deter criminal activity or you’re going to catch people.”

After this initial meeting, Larry decided to again go against the grain, and share crime data with Professor Janikowski’s team. Using this preliminary data, Professor Janikowski was able to build a pilot program to look into ways to reduce crime in the city. The results in the initial pilot were through the roof. The IBM report states,
“A few months later, that effort materialized into a three-day operation that proved to be one of the most effective ever. By identifying hot spots at a granular level, MPD made some 70 arrests in just the first two hours—a number usually made on an average weekend—and went on to make a total of 1,200, with crimes ranging from drugs to weapons charges to prostitution and other “quality-of-life” offenses.”

After the initial results, Larry realized the potential of the program, but knew that the success would require operational support from each department. To keep the program moving forward, Larry developed a business case for the mayor, highlighting the dire state of the budget, and the need to find solutions to complex problems in new and innovative ways.

“Godwin’s aim was to show how the intelligent alignment of police resources would effectively enable the department to close the manpower gap now—a must in the eyes of Memphis’s citizens. Under the plan Godwin proposed, each precinct commander in the MPD would be given the resources (in the form of overtime funding) and flexibility to make their own deployment decisions based on intelligence provided by the solution. Most importantly, results would be rigorously measured and commanders held accountable for their performance. It didn’t take much selling, because a few hours later, Godwin and the mayor were standing in front of the press touting the newly approved program—which came to be known as Blue CRUSH—as a way to intelligently reduce crime.”

Since Blue CRUSH has been implemented, there has been a decline in crime in Memphis. The City reports a decrease of 30% reduction of serious crime, and a 15% reduction in violent crime. Blue CRUSH allows the police department to be more productive and efficient how they use their crime data. The IBM report does a great job identifying how the system works, as the report mentions, the goal is to “police smarter, not harder,” here is an excerpt from the report:

“At the heart of it is a predictive model that incorporates fresh crime data from sources that range from the MPD’s records management system to video cameras monitoring events on the street. In the realm of crime-fighting analytics, there’s a fine line between the “interesting” and the actionable. It is strength in the latter that makes Blue CRUSH stand out from its predecessors.

Blue CRUSH lays bare underlying crime trends in the way that promotes an effective fast response, as well as a deeper understanding of the longer-term factors (like abandoned housing) that affect crime trends. It happens at the precinct level. Looking at multilayer maps that show crime hot spots, commanders can see not only current activity levels, but also any shifts in such activities that may have resulted from previous changes in policing deployment and tactics.

At each weekly meeting, commanders go over these results with their officers to judge what worked, what didn’t and how to adjust tactics in the coming week. They might see, for example, how burglaries are down in one ward, but up another, or where thieves are stealing cars in one ward and dumping them in another. What’s striking, says Godwin, is the granularity.

“We’re catching this immediately and we’re doing it every day,” he explains. “On short notice, we’re able to shift officers to a particular ward, on a particular day, right down to the shift level. It’s a bit like a chess match and it’s enabling us to make arrests we never could have before.”

This report is really a must read for those interested in predictive policing and crime prevention. It’s also a fascinating read for anyone looking for innovative ways to bring change within their organization. Larry’s actions provide a lot of great lessons on leadership that can be carried into your organization and help you push forward innovative and exciting programs.

Across the board, government is challenged to combat shrinking budgets with increasing citizen demand. With great case studies, such as the story of Memphis Police Department, we are all reminded that through solid leadership, innovative ideas, and a strong business case, the challenges can be met, and government can continue to provide the services demanded by citizens.

The IBM Analytics Solution Center (ASC) is part of a network of global analytics centers that provides clients with the analytics expertise to help them solve their toughest business problems. Check out their Analytics to Outcomes group on GovLoop.

Leave a Comment

10 Comments

Leave a Reply

Chris Cairns

This all makes perfect sense if you really think about it. Such a great write-up. Any other cities besides Memphis take this analytics-based approach to fighting crime?

Pat Fiorenza

Thanks, Chris. Make sure you check out the full article, it’s a really good read – I was shooting to just provide the highlights. It is truly amazing, when you think about all the data available to police departments, the ability to sort, filter and predict is really cool. I love reading these stories, would love to hear if anyone knows any other cities/projects using predictive policing.

We recently did a podcast with the City of Santa Cruz, also doing some predictive policing work. Check it out here:

https://www.govloop.com/profiles/blogs/could-big-data-help-prevent-crimes

David B. Grinberg

Interesting post, Pat. I would note that a contrarian might call that “racial/ethnic profiling”. This is because, based on the data, law enforcement may disproportionally target locations where most good citizens happen to be Black or Hispanic, for example — which may have a discriminatory or disparate impact. Just something to think about if you’re a racial or ethnic minority who lives in the targeted locations.

Pat Fiorenza

Hey David – interesting comment, would love to see any studies out there on the topic if you know of any, would be interesting to explore a little deeper. Could be one of the negative externalities of predictive policing, so it would be fascinating to learn how law enforcement agencies are avoiding having a discriminatory impact with predictive policing. Thanks for the comment.

Henry Brown

Interesting related from Internetevolution:
Chicago Turns to Analytics to Fight Gang Crime

Mayor Rahm Emanuel of Chicago is betting big that Facebook-style social network intelligence can tame the escalating gang violence in the nation’s third-biggest city, where 269 murders were recorded in the first half of 2012 — a 38 percent increase over 2011.

In New York, a city with a population nearly three times higher than Chicago’s, homicides fell 17 percent, to 194.

Here is the issue put bluntly: Can big-data analytics save lives in a city that is struggling with rising gang violence? A few weeks ago, that violence snuffed out the life of seven-year-old Heaven Sutton, apparently as one gangster shot at another.

Emanuel does not have many bets on this board. Budget cuts have disbanded the anti-gang police units that used to flood high-risk areas after an incident of gang violence. The mayor told the Associated Press that tactic did not work. “I don’t think coming in, swatting something down and letting it come back in two weeks is strengthening a community. What it does is build up cynicism.”

Police visionaries increasingly view CompStat as analytics 1.0 — “putting cops on the dots,” according to McCarthy. That’s because it generates red dots indicating where trouble has occurred, so police officers can then flood the area — the very tactic derided by Emanuel. Now, however, cops in Chicago and other cities, including Memphis, Minneapolis, and Los Angeles, are attempting to leverage big-data analytics to predict where crimes will occur. It’s an ambitious effort to pinpoint a location before a crime happens. That would indeed be a game changer.

The big question: Can big-data analysis techniques be applied to gang crime? Big-data has become extraordinarily efficient in predicting consumer behavior — if you buy soda XYZ when it is on sale, you are more likely to buy chips XYZ than chips PQR. An analyst who confirms this point has reams of data to prove the correlations. That helps merchandisers position products for still higher sell-through.

Pat Fiorenza

@Chris – I think that would be fascinating to look at. What other events may have happened over the time period that caused the crime to decrease? Was it Blue CRUSH or something else? With that said, one of things to always think through is what would have happen to crime without the implementation of Blue CRUSH? I am going to see if I can track down some studies, they would be interesting to take a look at statistically and just see the kind of data that is collected and analyzed.