Predictive Policing – fighting crime before it happens

August 21, 2010 by · 1 Comment 

No, this is not Minority Report, but it’s a step in that direction:

At universities and technology companies, scientists are working to develop computer programs that, in the most optimistic scenarios, could enable police to anticipate, and possibly prevent, many types of crime. Some of the most ambitious work is being done at UCLA, where researchers are studying the ways criminals behave in urban settings. One is trying to forecast the time and place of crimes using the same formulas that seismologists use to predict the distribution of aftershocks from an earthquake. Another builds computer simulations of criminals roving through neighborhoods to understand why they tend to cluster in certain areas and how they disperse when police go looking for them. “The naysayers want you to believe that humans are too complex and too random — that this sort of math can’t be done,” said Jeff Brantingham, a UCLA anthropologist. “But humans are not nearly as random as we think. In a sense, crime is just a physical process, and if you can explain how offenders move and how they mix with their victims, you can understand an incredible amount.”

About Peter

Comments

One Response to “Predictive Policing – fighting crime before it happens”
  1. Matt Osborne says:

    It’s basically crowd-management software applied to law-enforcement models. The same math that goes into analyzing how panicky people flee a burning building.