Anselm Hager, Krzysztof Krakowski, and Max Schaub find that exposure to ethnic violence negatively affects prosocial behavior within and across ethnic groups in Osh, Kyrgyzstan. In expanding upon their, work I demonstrate that on the contrary, ethnic violence can have a heterogenous treatment effect.
Compared to causal modeling, using Machine Learning techniques to predict violent civil conflict is nascent within the broader conflict literature. In this paper, Liz Masten and I run three Machine Learning models – OLS Regression, Ridge Regression, and Random Forest – on a dataset of our own making to predict instances of violent intrastate conflict.