Predictive Analytics

Who's the next head of Hezbollah? New platform has some predictions

STONE predictive analytics platform

University of Maryland scholars have developed a predictive analytics platform that can predict a criminal or terrorist organization's heir apparent.

A software platform developed by University of Maryland researchers can accurately predict who will rise to the top of terror or criminal organization after a top leader is killed, jailed or otherwise taken out of the operational picture.

The software, called the Shaping Terrorist Organizational Network Efficacy (STONE), is a graph database that could provide the national security and intelligence communities with a better understanding of the complex relationships that push leadership succession forward.

The researchers, led by V.S. Subrahmanian, a professor at the university's Institute for Advanced Computer Studies, used open source data to hypothetically test the STONE platform on four well-known terror groups, including al-Qaeda, Hamas, Hezbollah and Lashkar-e-Taiba (the group responsible for the 2008 attack on Mumbai, India).

Subrahmanian said the platform could predict with 80 percent accuracy which individual would ascend to a top leadership role when the sitting leader was removed from the position. The software draws its conclusions from unclassified data that included tidbits such as how long a person was actively involved with a particular group, their specific role and the roles of others which whom they directly associated.

Subrahmanian told FCW the information on the groups that formed the foundation of the platform was winnowed from worldwide news reports, data from scholarly papers and websites that track terrorists.

By predicting leadership changes, Subrahmanian said, STONE could also help refocus law enforcement and security agencies. Sometimes those groups become too fixed on a central figure as targets, when those individuals may be the hardest to get to. The database can show agencies that going after individuals in a group's second tier might weaken it more than capturing the top leader, he said.

Subrahmanian said he hopes to expand the capabilities of the platform, including the ability to do broader analysis of relationships of terror and criminal groups' operations. Government agencies that have access to even more detailed insider information could use STONE with even better accuracy.

The platform can be applied to other social groups as well, evaluating business as well as criminal networks. The next corporate CEO or the rising capo of a transnational drug cartel might also be predicted, but the researchers said those applications hadn't yet been tested.

Subrahmanian said he has not yet talked with the Homeland Security Department formally about the project, but hopes to soon.

About the Author

Mark Rockwell is a staff writer at FCW.

Before joining FCW, Rockwell was Washington correspondent for Government Security News, where he covered all aspects of homeland security from IT to detection dogs and border security. Over the last 25 years in Washington as a reporter, editor and correspondent, he has covered an increasingly wide array of high-tech issues for publications like Communications Week, Internet Week, Fiber Optics News, tele.com magazine and Wireless Week.

Rockwell received a Jesse H. Neal Award for his work covering telecommunications issues, and is a graduate of James Madison University.

Click here for previous articles by Rockwell. Contact him at mrockwell@fcw.com or follow him on Twitter at @MRockwell4.


Who are the Rising Stars?

Nominations for the 2016 Rising Star awards are now being accepted.

Featured

Reader comments

Wed, Aug 28, 2013 jim dandy germany

this map is similar to how different groups in the middle east get along

Please post your comments here. Comments are moderated, so they may not appear immediately after submitting. We will not post comments that we consider abusive or off-topic.

Please type the letters/numbers you see above

More from 1105 Public Sector Media Group