The Promise and Pitfalls of Conflict Prediction: Evidence from Colombia and Indonesia

56 Pages Posted: 30 Jul 2019

See all articles by Samuel Bazzi

Samuel Bazzi

Boston University - Department of Economics

Robert Blair

Brown University; Brown University - Watson Institute for International and Public Affairs

Christopher Blattman

University of Chicago, Harris School of Public Policy; National Bureau of Economic Research (NBER)

Oeindrila Dube

University of Chicago - Harris School of Public Policy

Matthew Gudgeon

Boston University

Richard Merton Peck

Northwestern University

Multiple version iconThere are 2 versions of this paper

Date Written: June 2019

Abstract

Policymakers can take actions to prevent local conflict before it begins, if such violence can be accurately predicted. We examine the two countries with the richest available sub-national data: Colombia and Indonesia. We assemble two decades of finegrained violence data by type, alongside hundreds of annual risk factors. We predict violence one year ahead with a range of machine learning techniques. Models reliably identify persistent, high-violence hot spots. Violence is not simply autoregressive, as detailed histories of disaggregated violence perform best. Rich socio-economic data also substitute well for these histories. Even with such unusually rich data, however, the models poorly predict new outbreaks or escalations of violence. "Best case" scenarios with panel data fall short of workable early-warning systems.

Keywords: Civil War, Colombia, conflict, Forecasting, Indonesia, Machine Learning, prediction

JEL Classification: C52, C53, D74

Suggested Citation

Bazzi, Samuel and Blair, Robert and Blattman, Christopher and Dube, Oeindrila and Gudgeon, Matthew and Peck, Richard Merton, The Promise and Pitfalls of Conflict Prediction: Evidence from Colombia and Indonesia (June 2019). CEPR Discussion Paper No. DP13829, Available at SSRN: https://ssrn.com/abstract=3428350

Samuel Bazzi

Boston University - Department of Economics ( email )

270 Bay State Road
Boston, MA 02215
United States

Robert Blair

Brown University ( email )

Box 1860
Providence, RI 02912
United States

Brown University - Watson Institute for International and Public Affairs

111 Thayer Street
Box 1970
Providence, RI 02912-1970
United States

Christopher Blattman

University of Chicago, Harris School of Public Policy ( email )

1101 East 58th Street
Chicago, IL 60637
United States

National Bureau of Economic Research (NBER) ( email )

1050 Massachusetts Avenue
Cambridge, MA 02138
United States

Oeindrila Dube

University of Chicago - Harris School of Public Policy ( email )

1155 E 60th St
Chicago, IL 60637
United States

Matthew Gudgeon

Boston University ( email )

595 Commonwealth Avenue
Boston, MA 02215
United States

Richard Merton Peck (Contact Author)

Northwestern University ( email )

2001 Sheridan Road
Evanston, IL 60208
United States

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
1
Abstract Views
222
PlumX Metrics