The Straw that Broke the Camel’s Back: Separating Close Calls from True Onsets in Conflict Prediction

Conflict forecasting seeks to correctly anticipate events of armed violence. While the field has made significant advancements, differentiating between close calls and true onsets has been overlooked despite its potential to improve our ability to predict new outbreaks of war. In this paper, we investigate why some countries with a high predicted risk of conflict experience limited violence only. We argue that the processes stalling the transition into more substantial levels of armed conflict display recurring patterns that can be leveraged to enhance conflict prediction. Against this background, we introduce a methodological innovation of the Shape finder aimed at separating the underlying processes of true onsets from stalling escalation, where low-intensity violence does not surpass a certain level. Based on the escalation spiral framework, we elaborate pathways to and away from conflict onset. Combining UCDP GED events with unpublished data on low-intensity violence, we apply a hurdle model to identify the dynamics that drive countries towards armed conflict. Our preliminary results indicate that the Shape finder is able to separate contexts that consistently lead to armed conflict from those where future intensity remains low, and that this information increases the model's ability to anticipate true onsets. Our findings highlight that the relationship between a predicted high conflict risk and subsequent onset of armed violence is context specific.