Mathematicians Gangs Program

November 2, 2011 by staff 

Mathematicians Gangs Program, At high levels of crime, gang-controlled areas such as Los Angeles Hollenbeck Division (which includes the neighborhoods of Boyle Heights, Lincoln Heights and El Sereno), can be difficult to understand even the most basic information about gang violence. That’s why UCLA created an algorithm that can fill in the blanks.

Working with the Police Department of Los Angeles, UCLA researchersanlyzed more than 1,000 gang crimes and crimes alleged gang members, many unresolved, over a period of 10 years in Hollenbeck, an area known for gang violence. The area is home to 30 gangs and nearly 70 gang rivalries, ie the list of possible suspects in the gang violence is soaring.

In developing the algorithm, simulated mathematical patterns of the bands, then excluded from the key information in the case (of the victim, aggressor, or both), leaving the algorithm to fill the missing information. The research is funded by the National Science Foundation, Division of the U.S. Army Office of Research on Mathematics, U.S. Office of Naval Research and the U.S. Air Force Office of Scientific Research.

“Our algorithm places the correct gang rivalry within the top three most likely rivalries that 80 percent of the time, which is significantly better than chance. This reduces a little, and that’s when we know nothing about crime victim or the perpetrator, “said Martin Short, UCLA Associate Professor of Mathematics and co-author of the study. Reduction of possible suspects allows police to focus their research on a much smaller area, saving time and labor.

The algorithm also ranked first in the correct band of the three results 50 percent of the time, higher than the percentage of 17 as a result of chance.

These results are just the beginning. “We can do even better. This is the first work for this new approach. We can only improve the 80 per cent for the development of more sophisticated,” said Andrea Bertozzi, lead study author and professor of mathematics and applied mathematics.

The algorithm can also be used for things beyond gang violence. “There are events – which could be crimes or anything else -. They are produced in a time series and a network of acquaintances there is activity between the nodes, in this case a gang attack another group with some of these activities, you know exactly who he was. involved and others not. That challenge of how to best educated opinion as to who was involved in the activities unknown, “said Bertozzi. These “cultural view [s]” could be used for anything where identities are unknown, from the identification of hackers to target consumers by advertising.

Report to Team

Please feel free to send if you have any questions regarding this post , you can contact on

Disclaimer: The views expressed on this site are that of the authors and not necessarily that of U.S.S.POST.


Comments are closed.