At LAPD, Predicting Crimes Before They Happen

Capt. Sean Malinowski of the Los Angeles Police Department does his crime-fighting in front of a computer screen.

He's in the LAPD's Real Time Analysis and Critical Response Division, located in a new crime data and analysis center in downtown Los Angeles. Malinowski is tracking two crimes that just occurred in south Los Angeles. Patrol cars are already on the scene. He says this facility is state of the art in real-time policing. He wants the force to be the best in predicting where criminals will strike.

For the past several years, Malinowski has worked with a team of researchers from UCLA. This month, they are rolling out a new computer program to do that. Using years of crime statistics, the computer churns out maps with small highlighted areas where it predicts a crime will occur.

Lt. Scott Harrelson drives to one of the areas, or boxes. When not on radio calls, officers in this northern patrol division of Los Angeles spend as much time as they can inside a box. Harrelson says officers won't do anything different there then they did before.

"It just means while they are in that box and in that area, they are going to be paying a lot more attention," he said.

So far it seems to be working. That's what Malinowski tells his officers at their morning muster.

"Let me tell you, we have week one results now that we looked at during the first week of this test — if you want to call it that — we had 30 of those crimes in the division reported," he told them.

Thirty property crimes, burglaries and car thefts — a 50 percent decrease compared to the same week last year, Malinowski says. He's not yet declaring predictive policing a success. He'll wait six months to do a complete analysis. But in Santa Cruz, Calif., the police department has used the UCLA program since July with similar results.

UCLA anthropologist Jeff Brantingham says he's not surprised. Human behavior, especially when in search of resources, follows very predictable patterns. For his doctoral work, Brantingham studied foraging strategies of ancient hunter-gatherers in Mongolia.

"It's surprising how similar the problems are," he said. "How it is that ancient hunter-gatherers found gazelles on the Mongolian steppes is very similar to how it is that offenders find a car to steal."

He says crime, especially property crime, happens in predictable waves.

"If your house is broken into, then the chance that it is going to be broken into again goes way up, and the chance that your neighbor's house is going to be broken into goes way up," he said.

That's because crooks now know the area and go back to where they had success. Brantingham says these crime waves show up in patterns similar to the aftershocks of an earthquake.

While the science is impressive, Loyola Law School professor Stan Goldman says he worries how the data will be used. Despite police assurances, he says, authorities could use it as reasonable doubt to stop and search innocent suspects who happen to be in the highlighted neighborhoods.

"It may very well end up reducing crime to a certain degree," he said. "The question is at what cost, at what price?"

Los Angeles police say the computer will never replace good policing practices, and that it's a much-needed tool, especially as budgets are cut and police forces are stretched thin.

Copyright 2011 National Public Radio. To see more, visit http://www.npr.org/.