Final Extra Credit Project

The toughest streets of Kent are to be found in these little pink boxes; that is, at least they are if you look at them through the crime-prediction software produced by PredPol. Crimes commonly committed in Kent, England show up on PredPol’s maps highlighted by pink squares. The predictions are very spot in, in fact, according to Mark Johnson, a police analyst: “In the first box I visited we found a carving knife just lying in the road.” PredPol is one of a range of tools using better data to predict the scene and possible cause of a crime. During a four-month trial in Kent, 8.5% of all street crime occurred within PredPol’s pink boxes, with plenty more next door to them; predictions from police analysts scored only 5%. However, PredPol also brings worries about privacy, and of justice systems run by machines not people. This brings up a worry that police officers will no longer have to really "do their job", but the computers will do it for them. Although, intelligent policing can convert these modest gains into significant reductions in crime. Within six months of introducing predictive techniques like PredPol in the Foothill area of Los Angeles, in 2011, property crimes had fallen 12% compared  with the previous year when it had not been used. The predictive approach works best against burglary and thefts of vehicles or their contents; crimes like these provide plenty of historical data to chew on, however, adding extra types of information, such as details of road networks, can fine-tune forecasts further. 

This is significant to me because both me, and my dad, are very interested in crime investigation and types of things like that, so I was very interested in anything related to that. I also think it is so fantastic that they have come up with a technology that actually gets officers ten times closer to catching criminals and solving serious crimes.

http://www.predpol.com