Predictive Modeling Research in LCCD Featured in Defense Publication

Predictive modeling research by V.S. Subrahmanian (pictured left), Francesca Spezzano and Aaron Mannes—all in the Laboratory for Computational Cultural Dynamics (LCCD)—was featured in an article in Defense One, a publication focused on defense and national security issues.

Their research focuses on predicting who could become the next leader of a terrorist organization. Using applied statistics, the research team has devised a system to predict the top three individuals—out of hundreds—most likely to become the next terrorist leader when the person in charge is removed.

The research team used carefully cultivated open-source data on four terrorist networks: al-Qaeda, Hamas, Hezbollah, and Lashkar-e-Taiba (the group associated with the 2008 terrorist attacks in Mumbai). Some of the variables they looked at include the role that the leader plays, such as fundraiser, spiritual leader or recruiter; how dangerous he was on the basis of hostility and capability; and the potential for retaliation in the event that he was taken out. The researchers’ method also predicts whether the group will become more dangerous after the succession, and how the terrorist network will evolve as a result.

A paper on their findings was published in the August 2014 issue of Communications of the ACM.

LCCD is one of 15 centers and labs in the University of Maryland Institute for Advanced Computer Studies.

Read more here.