How to Detect Criminal Gangs Using Mobile Phone Data
The study of social networks is providing dramatic insights into the nature of our society and how we are connected to one another. So it’s no surprise that law enforcement agencies want to get in on the act.
Criminal networks are just as social as friendship or business networks. So the same techniques that can tease apart the links between our friends and colleagues should also work for thieves, drug dealers, and organized crime in general.
But how would your ordinary law enforcement officer go about collecting and analyzing data in this way? Today, we get an answer thanks to the work of Emilio Ferrara at Indiana University in Bloomington and a few pals.
These guys have created a bespoke software platform that can bring together information from mobile phone records, from police databases and from the knowledge and expertise of agents themselves to recreate detailed networks behind criminal organizations.
The new platform, called LogAnalysis, gives a unique insight into the make up a criminal organization. “It allows forensic investigators to deeply understand hierarchies within criminal organizations, discovering members who play central role and provide connection among sub-groups,” they say.
One of the first problems any law enforcement agent is likely to come up against when studying social networks is the sheer volume of data that this process generates. This is where LogAnalysis comes into its own.
It automatically imports raw phone call records, removes ambiguities and redundancies in the data and then converts it to a format that can be easily displayed in the kind of visual graphic format that allows more detailed analysis. It also allows agents to add other data such as mug shots from police records and other information that the officer might have to hand.
The agents can then study the data in a number of different ways. For a start, they can look at the network of links between individuals according to the number of calls they make to each other.
In this network, each phone is a node and connections exist between phones that have called each other. That immediately allows the detection of communities that tend to contact each other more often. This in turn can reveal the hierarchy of a criminal organization and the most important individuals within it.
Of course, knowledge of the way criminal organizations work plays a crucial role in the analysis of this data. For example, people making the largest number of calls are not necessarily the ones in charge.
That’s because these gangs deliberately limit their communications so that the chiefs communicate their instructions to a small number of lieutenants who then distribute messages around the network. “Criminal networks heavily employ secrecy to escape investigations,” say Ferrara and co.
LogAnalysis also allows law enforcement officers to study the networks in limited time periods. That allows them, for example, to study the calls that are made just before and after a particular crime.
Ferrera and co illustrate their paper with an example of a large criminal network for which law enforcement agencies obtained records for 84 phones over a period of 15 days. This network was responsible for a series of robberies, extortions and illicit drug trafficking. Personal details were removed for privacy reasons.
Ferrera and co show how LogAnalysis reveals the links between members of this gang, how calls were clustered around specific crimes and how certain members operated in up to 14 different subgroups, some of which had the specific task of committing murders.
That’s an interesting, practical application for social network theory. And it raises a number of important questions about the nature of evidence in criminal investigations. In particular, to what extent can social networks be used as evidence of membership of a criminal organization?
Another question is where this data comes from and what kind of criminal network it applies to.
Given that three out of the four researchers on this paper are based at the University of Messina in Sicily, it’s not beyond the realms of possibility that the data comes from that part of Italy too. And if so, it’s not hard to imagine the kind of organization being described here.
Ref: arxiv.org/abs/1404.1295 : Detecting Criminal Organizations In Mobile Phone Networks
Geoffrey Hinton tells us why he’s now scared of the tech he helped build
“I have suddenly switched my views on whether these things are going to be more intelligent than us.”
Meet the people who use Notion to plan their whole lives
The workplace tool’s appeal extends far beyond organizing work projects. Many users find it’s just as useful for managing their free time.
Learning to code isn’t enough
Historically, learn-to-code efforts have provided opportunities for the few, but new efforts are aiming to be inclusive.
Deep learning pioneer Geoffrey Hinton has quit Google
Hinton will be speaking at EmTech Digital on Wednesday.
Get the latest updates from
MIT Technology Review
Discover special offers, top stories, upcoming events, and more.