Thursday, August 19, 2010

UPenn Professor Predicting Criminal Behavior

Richard Berk, a professor at the University of Pennsylvania, has developed new crime prediction software intended to reduce the rate of many crimes including murder.

Predicting future crimes does sound, well, futuristic, Berk told Discovery Magazine. Even his students at the University of Pennsylvania compare his research to the Tom Cruise movie "Minority Report."

In the interest of full disclosure, I earned a Master Degree in Criminology at the University of Pennsylvania in 2009. I had the pleasure of working with faculty members who were working directly with Professor Berk. The work being done at Penn is extraordinary.

Nevertheless, Berk said, it is more "Like trying to find the needle in the haystack" than the glitzy work portrayed in Minority Report.

Discovery Magazine goes into detail explaining the genesis of Berk's work. Beginning several years ago, the researchers assembled a data set of more than 60,000various crimes, including homicides. Using an algorithm they developed, they found a subset of people much more likely to commit homicide when paroled or probated. Instead of finding one murderer in 100, the UPenn researchers could identify eight future murderers out of 100.

Berk's software examines roughly two dozen variables, from criminal record to geographic location. The type of crime, and more importantly, the age at which that crime was committed, were two of the most predictive variables.

"People assume that if someone murdered then they will murder in the future," Berk told Discovery. "But what really matters is what that person did as a young individual. If they committed armed robbery at age 14 that's a good predictor. If they committed the same crime at age 30, that doesn't predict very much."

Baltimore and Philadelphia are already using Berk's software to help determine how much supervision parolees should have. Washington, D.C. is now set to use the algorithm to help determine lesser crimes as well. If those tests go well, Berk told Discovery the program could help set bail amounts and suggest sentencing recommendations.

My Take

Predicting all human behavior is impossible. If we could predict human behavior there would be no crime. No matter how effective the predictive instruments there will be outliers. There will be people who kill or maim who were not being incapacitated (in jail) or subject to intensive supervision because the predictive tools indicated a low risk.

Unfortunately, those outliers often control the political debate. The knee-jerk reaction by policymakers often does more harm than good. Dr. Berk's predictive model is an evidenced based practice that is supported by rigorous research. His model promises to reduce recidivism and victimization. Yet, it is not foolproof and hopefully those who make the laws and implement policy understand and account for that simple truth.

To read more:

No comments:

Post a Comment