UCLA writes computer program to battle East L.A. gangs
A team of UCLA researchers has once again delved into the world of crime fighting, this time developing a computer program capable of pointing police in the right direction when rivalries between street gangs erupts into violence and crime.
The university announced Monday that mathematicians have devised a complex algorithm that crunched information from the Los Angeles Police Department on more than 1,000 gang-related crimes and suspected gang crimes in the LAPD’s Hollenbeck Division -- an area of East L.A. that is home to more than two dozen active gangs.
The goal was to bring some mathematical order to the murky, shifting gang landscape in Hollenbeck, where rivalries and alliances between groups are difficult to track.
By sifting through a decade of crime data and searching for otherwise undetectable patterns, the algorithm was designed to identify which gangs were most likely involved in crimes.
To test it, the researchers created an imaginary set of crime data that closely mirrored the actual shootings, assaults and other crimes in the Hollenbeck Division. They then removed pieces of important information — either the name of the victim, the perpetrator or both — and tested whether the computer algorithm could come up with the missing data.
About 80% of the time, the high-powered calculations were able to identify the three gangs that were most likely to have committed a crime against a rival.
"That narrows it down quite a bit,” said Martin Short, co-author of the study, in an announcement released by UCLA. It is, he said, “significantly better than chance.”
"If police believe a crime might have been committed by one of seven or eight rival gangs, our method would look at recent historical events in the area and compute probabilities as to which of these gangs are most likely to have committed crime," said the study's senior author, Andrea Bertozzi, director of applied mathematics at UCLA.
The same mathematics used to map gang rivalries can be used in other areas of law enforcement and other industries, such as tracking computer hackers or improving advertisers’ ability to target customers, Bertozzi said.
Put simply, wherever there are distinct events that occur in a certain time frame and involve members of a distinct group, it is possible to use the mathematics to come up with the probability that a certain member of the group is involved.
The team of researchers has been picking apart other types of crime data as well. They have built a mathematical model that allows them to identify crime hotspots, and predict how those areas would respond to an influx of police officers.
A Times article last year profiled their efforts to devise another predictive algorithm -- one that eventually could enable police to anticipate, and possibly prevent, many types of crimes.
The LAPD has positioned itself at the center of the quickly emerging field of predictive policing, sharing crime data with the UCLA researchers and seeking federal grants to run pilot programs within the department.
The latest research can be found on the website of the mathematical journal Inverse Problems, which will publish the findings in a future print edition, the university said.
Photo: LAPD Det. Dan Jaramillo, assigned to Hollenbeck gang unit, checks graffiti for clues on solving crimes. Now UCLA researches have come up with an algorithm for crime solving. Credit: Ken Lubas/Los Angeles Times.