Promising Practices Promising PracticesPromising Practices
A forum for government's best ideas and most innovative leaders.

How Local Governments Are Cutting Burglaries by 27 Percent


Police departments across the U.S. are piloting crime prevention programs that rely on a smart analysis of historical crime data in neighborhoods across their cities. And they are finding that they can cut burglaries by as much as 27 percent!

City police departments across the country are turning traditional police officers into “data detectives.”  Police departments across the country have adapted business techniques --  initially developed by retailers, such as Netflix and WalMart, to predict consumer behavior -- to predict criminal behavior.  A new IBM Center report, by Dr. Jennifer Bachner at Johns Hopkins University, tells compelling stories of the experiences three cities -- Santa Cruz, CA; Baltimore County, MD; and Richmond, VA – are having in using predictive policing as a new and effective tool to combat crime.

Predictive Analytics Reach Beyond Policing.

While this report focuses on the use of predictive techniques and tools for preventing crime in local communities, these techniques and tools are being applied to other policy arenas, as well, such as the efforts by the Department of Housing and Urban Development to predict and prevent homelessness, and the Federal Emergency Management Agency’s efforts to identify and mitigate communities vulnerable to natural disasters.

Dr. Bachner says that predictive analytics – in policing or other policy areas – is not a silver bullet.  It is an additional tool that supplements existing methods.  For example, community policing – where officers build trust and neighborhood-level relations -- is an important strategy for deterring crime.  “Nevertheless,” she notes, “policing, like many other fields, is undoubtedly moving in a data-driven direction.”

Santa Cruz, CA, Is a Pioneer.

The Santa Cruz, California Police Department (SCPD) was one of the first in the U.S. to embed predictive policing in its regular, day-to-day operations.  A pilot began in mid-2011 and expanded to the entire city by mid-2012.  In the pilot phase, burglaries dropped by 27 percent when compared to the previous year.

What did they do?  According to Bachner:

“The core of the SCPD program is the continuous identification of areas that are expected to experience increased levels of crime in a specified time-frame.  A computer algorithm draws upon a database of past criminal incidents to assign probabilities of crime occurring to 150 by 150 meter square cells on a map of Santa Cruz.  The database includes the time, location and type of each crime committed.

In the calculations of probabilities, more recent crimes are given greater weight.  The program then generates a map that highlights the 15 cells with the highest probabilities.  Prior to their shifts, officers are briefed on the locations of these 15 cells and encouraged to devote extra time to monitoring these areas.  During their shifts, officers can log into the web-based system to obtain updated, real-time, hot-spot maps.”

In an article in the local paper, Santa Cruz Deputy Police Chief Steve Clark said: "It's almost like Neighborhood Watch in the next century."

But having the technology doesn’t mean it will get used, notes Dr. Bachner.   Analytic techniques such as hierarchical and partitioned clusters can be intimidating to non-analysts.  She found that getting buy-in by the on-the-street police officer was crucial.  Otherwise, the data would not be used.  She says “there cannot be top-down implementation; it cannot be imposed on unwilling officers as a replacement for experience and intuition.”   She says that once officers began using it to supplement their traditional approaches, they liked the positive results.  She also said that with staff cuts of 20 percent in recent years as a result of budget constraints, that the new approach made the force more efficient.

Lessons Learned. 

Dr. Bachner’s observations of the adoption of predictive policing by Santa Cruz and other communities led to several insights.  These insights probably hold true in other policy arenas, as well:

  • First, just get started.  It is a cost-effective way to “do more with less.”  Initial start up costs are typically recovered quickly.
  • Second, predictive policing should be treated as an addition to, not a substitute for, traditional policing methods.  She says top-down implementation is often unsuccessful:  “officers were most likely to incorporate predictive methods into their decision-making when they were motivated to do so by their peers rather than their supervisors.”
  • Third, make the software available to frontline officers.  One of the biggest advantages is access to real-time information, such as maps, which needs to be accessible while in their cars or foot patrol.
  • And finally, designate “champions” committed to the use of analytics as a way of doing business.  In Richmond, VA, this was its crimes analysis unit.  This unit split analysts’ time between analysis and serving in an assigned precinct.  As a result, they were able to communicate readily with other officers and provide on-the-job training on analytic techniques.

John M. Kamensky is a Senior Research Fellow for the IBM Center for the Business of Government. He previously served as deputy director of Vice President Gore's National Partnership for Reinventing Government, a special assistant at the Office of Management and Budget, and as an assistant director at the Government Accountability Office. He is a fellow of the National Academy of Public Administration and received a Masters in Public Affairs from the Lyndon B. Johnson School of Public Affairs at the University of Texas at Austin.

Close [ x ] More from GovExec

Thank you for subscribing to newsletters from
We think these reports might interest you:

  • Sponsored by G Suite

    Cross-Agency Teamwork, Anytime and Anywhere

    Dan McCrae, director of IT service delivery division, National Oceanic and Atmospheric Administration (NOAA)

  • Data-Centric Security vs. Database-Level Security

    Database-level encryption had its origins in the 1990s and early 2000s in response to very basic risks which largely revolved around the theft of servers, backup tapes and other physical-layer assets. As noted in Verizon’s 2014, Data Breach Investigations Report (DBIR)1, threats today are far more advanced and dangerous.

  • Sponsored by One Identity

    One Nation Under Guard: Securing User Identities Across State and Local Government

    In 2016, the government can expect even more sophisticated threats on the horizon, making it all the more imperative that agencies enforce proper identity and access management (IAM) practices. In order to better measure the current state of IAM at the state and local level, Government Business Council (GBC) conducted an in-depth research study of state and local employees.

  • Sponsored by Aquilent

    The Next Federal Evolution of Cloud

    This GBC report explains the evolution of cloud computing in federal government, and provides an outlook for the future of the cloud in government IT.

  • Sponsored by LTC Partners, administrators of the Federal Long Term Care Insurance Program

    Approaching the Brink of Federal Retirement

    Approximately 10,000 baby boomers are reaching retirement age per day, and a growing number of federal employees are preparing themselves for the next chapter of their lives. Learn how to tackle the challenges that today's workforce faces in laying the groundwork for a smooth and secure retirement.

  • Sponsored by Hewlett Packard Enterprise

    Cyber Defense 101: Arming the Next Generation of Government Employees

    Read this issue brief to learn about the sector's most potent challenges in the new cyber landscape and how government organizations are building a robust, threat-aware infrastructure

  • Sponsored by Aquilent

    GBC Issue Brief: Cultivating Digital Services in the Federal Landscape

    Read this GBC issue brief to learn more about the current state of digital services in the government, and how key players are pushing enhancements towards a user-centric approach.


When you download a report, your information may be shared with the underwriters of that document.