The paper considers univariate and multivariate models to forecast monthly conflict events in the Sudan over the out-of-sample period 2009 – 2012. The models used to generate these forecasts were based on a specification from a machine learning algorithm fit to 2000 – 2008 monthly data. The...

Though recent literature uncovers linkages between commodity prices and conflict, the causal direction of the relationship remains ambiguous. We attempt to contribute in this strand of research by studying the dynamic relationship of commodity prices and the onsets of conflict events in Sudan....