Computer model forecasts crime sprees
NewScientist.com news service, Aug. 17, 2003
A more powerful tool for forecasting crime is emerging from a huge electronic database of six million crimes.
A team from Carnegie Mellon University analyzed the data in two ways: A statistical analysis that spots broad trends allowed researchers to quantify the rules of thumb that police officers often learn from experience; and a list leading indicators -- minor offences such as vandalism and trespassing that crime analysts believe precede more serious crimes.
The model succeeded in forecasting crime rates with an error of between 10 and 20 per cent.
http://www.newscientist.com/news/news.jsp?id=ns99994050