Abstract

This paper aims to examine how the regional variable in country conflict modeling affects forecast accuracy and identifies a methodology to further improve the predictions.Design/methodology/approachThis paper uses statistical learning methods to both evaluate the quantity of data for clustering countries along with quantifying accuracy according to the number of clusters used.FindingsThis study demonstrates that increasing the number of clusters for modeling improves the ability to predict conflict as long as the models are robust.Originality/valueThis study investigates the quantity of clusters used in conflict modeling, while previous research assumes a specific quantity before modeling.