Too late to catch OJ but still a potentially significant advancement in law enforcement: using artificial intelligence software to predict killers before they strike.

University of Pennsylvania criminologist Richard Berk, a trained statistician, never met a data set he didn't like.

Now, using fresh data from the Philadelphia probation department, Berk and three colleagues have built an innovative model for predicting which troublemakers already in the system are most likely to kill or attempt a killing.

With the homicide rate in Philadelphia outpacing last year's by at least 7 percent, a computer model for "forecasting murder" is in the works, Berk said, to be delivered to the probation department in the new year, with clinical trials of the new tool to begin in the spring.

Initial research suggests the software-based system can make it 40 times more likely for caseworkers to accurately predict future lethality than they can using current practices.

The project is funded with a private grant and the software is in the public domain, so the product will be delivered to the city free.

I think we should apply this sort of software to everyone with a criminal record, not just those on probation. There's no difference between using AI software and using human intelligence to reach the same conclusions, except that software is cheaper and less biased than are humans, so the results should be more accurate.

Remember, the system doesn't predict specific murders, only which people are likely to commit murders in the future. So what do we do with those people once we think we've found them? Keep a close eye on them till they get too old to cause trouble, I guess. I wouldn't be adverse to attaching ankle monitors to petty crooks who are predicted to eventually escalate.

(HT: Slashdot and Nick.)



Email blogmasterofnoneATgmailDOTcom for text link and key word rates.

Site Info