Understanding Patterns of Terrorism in India Using AI Machine Learning

Abstract With the tremendous increases in Artificial Intelligence (AI) computing technology capabilities, application of AI approaches to terrorist data can yield useful insights into the interaction of terrorists, governance, and geography. There have been few applications of machine learning techniques to understanding patterns of terrorist behavior. Specifically, little work has been done to analyze terrorism patterns in India, which experiences one of the world's highest levels of terrorism. We apply “shallow AI models” to a decade of terrorist incidents in India. We show that AI approaches generate highly accurate models that predict levels of violent incident behavior across locations from a history of past attacks, and identify the principal factors correlated with a location being targeted. This study provides an example of socially-relevant AI research, expands our understanding of the dynamics of terrorism in a way that can help to shape counterterrorism policy and contributes to our greater recognition of the interwoven relationship of technology, knowledge, and society.
  • Dinesh Verma (IBM US)
  • Rithvik Yarlagadda (PSU)
  • Scott Sigmund Gartner (PSU)
  • Diane Felmlee (PSU)
  • Dave Braines (IBM UK)
Date Sep-2019
Venue Annual Fall Meeting of the DAIS ITA, 2019