STOP software predicts terror groups' reasoning and actions

The terrorism prediction software of ISR-affiliated Professor V.S. Subrahmanian is being featured in leading information technology magazines. Subrahmanian is the director of the University of Maryland's Institute for Advanced Computer Studies (UMIACS).

Subrahmanian's SOMA Terror Organization Portal (STOP) is being used to suggest high-level strategies for dealing with major terrorist organizations. (SOMA stands for Stochastic Opponent Modeling Agents.) The data mining software helps predict how terror groups will act and share data through social networking. It provides methods for reasoning about terror groups and forecasting what they might do in the future. It contains unique social networking capabilities that allow analysts to effectively cooperate to better understand and counteract terror groups.

"The software takes either a hypothetical or true situation, and tries to predict how a group might act based on what has actually happened," Subrahmanian says. "We achieved accuracy on the order of about 90-plus percent ... but the predictions are somewhat coarse grained."

STOP research is conducted by UMIACS' Lab for Computational Cultural Dynamics.

Read about STOP in these articles:

| Computerworld Magazine | IT Week | Network World |

Published March 3, 2008