Published in News

Cops opting for Minority Report style predictions

by on31 July 2012

Computer says where the crime is

Police are turning to computer predictions of crime in a similar way to Minority Report. In that flick, a scientologist with a nice wife found himself policing a system where psychics would predict when and where a crime would happen and he would have to show up to arrest the person before the committed it.

But now, according to AP, police have managed to come up with software which looks at algorithms to predict when a crime will happen. Colleen McCue, a behavioural scientist at GeoEye told APL that studying criminal behaviour was not that different from examining other types of behaviour like shopping. McCue said that criminals will go to places that they think they will be successful. While it is impossible to use the software to predict exactly when a crime will take place the technology could help in cities where tight budgets were forcing patrol reductions.

The system depends on getting as much data as possible to determine patterns. This can be especially useful in property crimes like auto theft and burglary, where patterns can be detected. Then the computer builds a model that factors in attributes like the time of year, whether it is hot and humid or cold and snowy, if it is a payday when people are carrying a lot of cash. IBM has a unit for developing this sort of software. The head of it, Mark Cleverly, said that the software can predict if a town  can expect a wave of vehicle thefts. We guess the computer should factor in if Nosher the TeaLeaf has just been let out of jail.

IBM has worked with dozens of agencies such as London's Metropolitan Police, the Polish National Police and a number of US and Canadian cities using the software. Apparently in Memphis, officials said serious crimes fell 30 per cent and violent crimes declined 15 per cent since implementing predictive analytics in a program with IBM and the University of Memphis in 2006. The software called CRUSH - Criminal Reduction Utilising Statistical History - targeted certain "hot spots" to allow police to deploy more efficiently. In one case police found an organised crime operation which no one knew existed. By crunching the numbers, police were able to pinpoint the zone and time of likely holdups and caught a group of robbers in the process of carrying out the robbery.

Rate this item
(0 votes)