Predictive Policing: Skill + technology = crime reduction

Print Friendly
↓Watch: Manchester’s predictive policing platform.↓


MANCHESTER, NH

Screen Shot 2015-11-04 at 5.28.00 PM


MANCHESTER, NH – Forecasting crime sounds more like a plot-line from an action thriller than an everyday function of Manchester Police Department. But since adopting predictive analytics as part of their everyday approach to community policing, police officers find they are able to prevent crime rather than simply chase it down.

It’s cutting-edge technology that has put Manchester on the map, based on the buy in, from Chief Nick Willard on down the chain of command.

Since rolling out the department’s predictive policing model mid-summer crime statistics took a remarkable slide – robberies were down 24 percent, burglaries were down 13 percent and thefts from cars were down 34 percent, amounting to a 28 percent overall reduction in crime.

The department worked with IBM and a team from Ironside Data Science & Analytics  to create the predictive modeler, which transmits a real-time data map to officers on patrol.

Here’s the rundown on what’s been accomplished so far:

  • Forecasts for each 8-hour officer shift, allowing appropriate resource allocation, and daily updates to the hot spot maps so forecasts are continually accurate to seven days out.
  • Workflows for pushing hot spot maps out to the mobile data terminals (MDTs) in Manchester PD cruisers so officers can see where hot spots are predicted on the go in near real-time.
  • Crime reductions of 24 percent  for robberies, 13 percent for burglaries, and 34 percent for thefts from motor vehicles within the first 10 weeks of deployment.
  • Recorded a total crime reduction of 28 percent within the first five weeks of deployment.
  • Recorded 60 percent crime prediction accuracy within a 500-foot radius of where the crime was forecast to occur.

Predictive-Policing-Options


More visibility in the predictive crime areas is key, says Willard, who is putting visible resources wherever a crime is expected to occur, based on the data.

“It could be doing a park and walk, or simply having an officer park in a particular area to do paperwork.

Willard credits Officer Matt Barter, who brought the idea to the police department as part of a master’s thesis he was working on at Boston University.

“As soon as we heard about it, we reassigned Officer Barter as a crime analyst, and he started working with IBM, and its just taken off,” said Willard.

Although the chief declined an invitation by IBM to fly to Las Vegas to talk about how the program is working in Manchester, he did participate in an 11-minute video (see above) outlining how the platform works.

Willard says he is looking forward to seeing how the data looks by the end of the year.


email boxYou’re one click away! Sign up for our free eNewsletter and never miss another thing

 

About Carol Robidoux 5210 Articles
Journalist and editor of ManchesterInkLink.com, a hyperlocal news and information site for Manchester, NH.