A Generative Model For Predicting Terrorist Incidents

Abstract A major concern in coalition peace-support operations is the incidence of terrorist activity. In this paper, we propose a generative model for the occurrence of the terrorist incidents, and illustrate that an increase in diversity, as measured by the number of different social groups to which that an individual belongs, is inversely correlated with the likelihood of a terrorist incident in the society. A generative model is one that can predict the likelihood of events in new contexts, as opposed to statistical models which are used to predict the future incidents based on the history of the incidents in an existing context. Generative models can be useful in planning for persistent Information Surveillance and Reconnaissance (ISR) since they allow an estimation of regions in the theater of operation where terrorist incidents may arise, and thus can be used to better allocate the assignment and deployment of ISR assets. In this paper, we present a taxonomy of terrorist incidents, identify factors related to occurrence of terrorist incidents, and provide a mathematical analysis calculating the likelihood of occurrence of terrorist incidents in three common real-life scenarios arising in peace-keeping operations.
Authors
  • Dinesh Verma (IBM US)
  • Archit Verma
  • Diane Felmlee (PSU)
  • Gavin Pearson (Dstl)
  • Roger Whitaker (Cardiff)
Date Sep-2017
Venue 1st Annual Fall Meeting of the DAIS ITA, 2017
Variants