Researchers at the University of Marylands Institute for Advanced Computer Studies have put these findings on an internet portal giving access to experts to accurately forecast potential steps of terrorists after analysing their previous behaviour patterns. Stochastic Opponent Modeling Agents (SOMA) has prepared likely behaviours of several terror outfits, including Hezbollah, Hamas and Hezb-I-Islami. In collaboration with computer experts and political scientists, it has found probability of each of the organisations taking certain actions in different situations.
SOMA Terror Organisation Portal will automatically learn the rules that activities of terrorist outfits follow and will set up network with other analysts examining the same subjects, researchers say.
SOMA is a computer science and social science achievement that will facilitate learning about and forecasting terrorist group behaviors based on rigorous mathematical and computational models, VS Subrahmanian of UMIACS said.