Big Data Fights Crime

Recently, the Memphis Police Department has been successful in reducing crime after launching Blue CRUSH (Crime Reduction Utilizing Statistical History) in collaboration with the University of Memphis. Blue CRUSH allows the department to look at a radius and determine how likely crimes are to occur there based on previous crime occurrences. This allows officers to be sent to areas where their presence will be more helpful. 

The command center for Blue CRUSH is comprised of 20 dual-monitor workstations and 42 rear-projection 50-inch displays that receive surveillance imagery from 400 video cameras stationed throughout the city. It is monitored 24/7, and the data collected is shared with a team from the University of Memphis who analyze the data using SPSS and Crime Mapping software published by the Omega Group. 

The center is also working on the Automated Case Examination Service (ACES), which keeps compiled information so that officers responding to 911 calls have easy access to pertinent information about suspects (accomplices, acquaintances, friends and auto registration information), as well as victims.  

If these two programs were rolled out to other cities, it could help to drastically reduce crime. 

This entry was posted in Uncategorized. Bookmark the permalink.

1 Response to Big Data Fights Crime

  1. cbaughma says:

    This crime-fighting tactic is very interesting, and I believe it will help reduce crime for a considerable amount of time. My only concern in implementing a procedure like such is regarding time. I believe the predictive model will work in reducing crime for a couple of years in that they will know where to send the most officers according to where the data shows the most crimes to occur. However, over time, I believe criminals may catch on to the trend discovery process, and instead they may purposely target their crimes to areas that once had no crime and therefore are not factored into the predictive model. In using big data to predict and combat crime, modelers must work hard to ensure the model is robustly designed and forward-looking regarding potential model limitationsl

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Google photo

You are commenting using your Google account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s