Analysts believe that insurgents in Afghanistan form similar networks to street gangs in the US. So the software for analysing these networks abroad ought to work just as well at home, say military researchers.

To that end, these guys have created a piece of software called the Organizational, Relationship, and Contact Analyzer or ORCA, which analyses the data from police arrests to create a social network of links between gang members.

The new software has a number of interesting features. First it visualises the networks that gang members create, giving police analysts a better insight into these organisations.

It also enables them to identify influential members of each gang and to discover subgroups, such as “corner crews” that deal in drugs at the corners of certain streets within their area.

The software can also assess the probability that an individual may be a member of a particular gang, even if he or she has not admitted membership. That’s possible by analysing that person’s relationship to other individuals who are known gang members.

The software can also find individuals known as connectors who link one gang withanother and who may play an important role in selling drugs from one group to another, for example.

Paulo and co have tested the software on a police dataset of more than 5400 arrests over a three-year period. They judge individuals to be linked in the network if they are arrested at the same time.

This dataset revealed over 11,000 relationship among. From this, ORCA created a social network consisting of 1468 individuals who are members of 18 gangs. It was also able to identify so-called “seed sets”, small groups within a gang who are highly connected and therefore highly influential.

Ref: How Military Counterinsurgency Software Is Being Adapted To Tackle Gang Violence in Mainland USA – MIT Technology Review
Ref: Social Network Intelligence Analysis to Combat Street Gang Violence – Research Paper