The summer research project at START involved pattern recognition in two large terrorism related databases, namely the Global Terrorism Database (GTD) and the Profiles of Incidents Involving CBRN by Non-State Actors (POICN) Database, employing neural networks and other machine learning algorithms. Training and test data subsets were extracted from previously compiled data to develop a variety of models based on machine learning pattern recognition algorithms that can enable prediction of future terrorist threats with specified percentage errors and uncertainties and thereby enable the intelligence and homeland security communities to make informed decisions regarding deployment of counter-terrorism resources in order to effectively thwart terror plots prior to their occurrence.
Garchia-Sanchez, Raul, Daniel Casimir, and Prabhakar Misra. 2014. "Innovative Algorithm and Database Development Relevant to Counterterrorism and Homeland Security Efforts at START." National Consortium for the Study of Terrorism and Responses to Terrorism (START) Report, University of Maryland, College Park, MD (August). https://www.start.umd.edu/sites/default/files/publications/local_attachments/Prabhakar%20Project%20%231.pdf