Description
Book SynopsisThis book should be useful to anyone interested in identifying the causes of civil conflict and doing something to end it. It even suggests a pathway for the lay reader. Civil conflict is a persistent source of misery to humankind. Its study, however, lacks a comprehensive theory of its causes. Nevertheless, the question of cooperation or conflict is at the heart of political economy. This book introduces Machine Learning to explore whether there even is a unified theory of conflict, and if there is, whether it is a good' one. A good theory is one that not only identifies the causes of conflict, but also identifies those causes that predict conflict. Machine learning algorithms use out of sample techniques to choose between competing hypotheses about the sources of conflict according to their predictive accuracy. This theoretically agnostic picking' has the added benefit of offering some protection against many of the problems noted in the current literature; the tangled causality betw
Trade ReviewIn Predicting Hotspots: Using Machine Learning to Understand Civil Conflict James T. Bang, Atin Basuchoudhary, John David, and Tinni Sen provide a vital contribution to the social scientific study of civil wars and other forms of violence within states. Whereas most theoretical and empirical studies of intrastate conflicts emphasize the correlates or the causes of violence, this book offers a variety of standard and innovative methodologies to best predict future civil wars. The book is a must-have for scholars and policymakers concerned about predicting future civil wars and what can be done to prevent them. -- Charles H. Anderton, College of the Holy Cross
Predicting Hotspots: Using Machine Learning to Understand Civil Conflict is an ambitious and successful demonstration of how machine learning can be employed towards a holistic understanding of civil conflict. It provides a concise and intuitive introduction to machine learning using conflict data. In so doing, the top socioeconomic predictors of civil conflict are identified. Of equal or greater value is the authors’ insightful discussion of how their findings can better inform policy making and theoretical model selection. -- Dann Arce, University of Texas at Dallas
Basuchoudhary, Tinni, Bang and David make a compelling case for using machine learning to predict conflict. The book is a timely and very welcome addition to our knowledge on the correlates of conflict. -- Günther Schulze, Professor of Economics, University of Freiburg
Table of ContentsChapter 1: An Overview of the Literature review Chapter 2: An Overview of Machine Learning Techniques Chapter 3: A Description of Our Variables Chapter 4: Preparing the Data Chapter 5: Implementing Machine Learning to Predict Conflict Using R Chapter 6: Models and Results Chapter 7: Choosing Among Seminal Models of Conflict Theory Chapter 8: Choosing between Microeconomic Models of Conflict Chapter 9: Bargaining Failure, Commitment Problems, and The Likelihood of Conflict Chapter 10: Toward a Predictive Theoretical Model of Civil Conflict: Some Speculation
