A Machine Learning Based Model of Boko Haram

A Machine Learning Based Model of Boko Haram brings computational methods into one of the most urgent security problems of the last decade. Written by V. S. Subrahmanian, Chiara Pulice, James F. Brown, and Jacob Bonen-Clark, this Springer volume examines Boko Haram through the lens of machine learning, temporal probabilistic rules, and data-driven policy analysis.

What this book focuses on

The book reduces Boko Haram’s activity to structured monthly data and uses that evidence to study patterns in attacks, escalation, and related conditions. It pays particular attention to sexual violence, suicide bombings, abductions, arson, and other forms of violence, showing how computational modeling can help identify likely behavior and explain why a prediction is being made.

Why the approach matters

Rather than treating the subject as history alone or as abstract theory, the book connects analysis to forecasting. That makes it especially relevant for readers who want to understand how machine learning can support counter-terrorism research, security analysis, and public policy thinking without losing sight of the underlying real-world threat.

Inside the structure

• A historical overview of Boko Haram
• Temporal Probabilistic rules and policy computation methods
• Focused chapters on major attack types and behavioral patterns
• Discussion of predictive findings and policy implications

Who will find it useful

This ebook is a strong fit for readers interested in machine learning, data science, predictive modeling, terrorism studies, African security issues, and policy research. It is especially useful for analysts and advanced readers who value explainable computational approaches to security problems.

If you are looking for a rigorous, research-based ebook that treats Boko Haram with both analytical depth and methodological clarity, this title belongs on the shortlist.