Predicting the severity of civil wars
with Nils W. Metternich, Altaf Ali, Gokhan Ciflikli, Gareth Lomax and Sigrid Weber
Abstract. We introduce an actor-centric approach to predict the severity of conflict one month into the future. We argue that the prediction of conflict severity needs to focus on the actors that are responsible for conducting armed violence. Hence, we predict the severity of conflict in government-rebel organization dyads. Our predictors focus especially on rebel organization characteristics, behaviour, and the conflict networks actors are embedded in. Our statistical learning approach relies on random forests to predict the severity of conflict. We demonstrate that our model performs especially well in distinguishing high levels of severity from very low levels, and yields better predictions that geography-based prediction models.
Read the latest draft here.