Forecasting Change in Conflict Fatalities with Dynamic Elastic Net

TL;DR

This paper presents a novel adaptive modeling approach using Dynamic Elastic Net to forecast conflict fatalities, accounting for complex, country-specific conflict drivers and providing interpretable, dynamic predictions with over 700 variables.

Contribution

It introduces a country-specific, adaptive forecasting method that efficiently handles large covariate sets and enhances interpretability of conflict drivers over time.

Findings

Effective in modeling conflict dynamics across countries

Selects relevant predictors for each country, improving interpretability

Addresses complexity with computational efficiency

Abstract

This article illustrates an approach to forecasting change in conflict fatalities designed to address the complexity of the drivers and processes of armed conflicts. The design of this approach is based on two main choices. First, to account for the specificity of conflict drivers and processes over time and space, we model conflicts in each individual country separately. Second, we draw on an adaptive model -- Dynamic Elastic Net, DynENet -- which is able to efficiently select relevant predictors among a large set of covariates. We include over 700 variables in our models, adding event data on top of the data features provided by the con-venors of the forecasting competition. We show that our approach is suitable and computa-tionally efficient enough to address the complexity of conflict dynamics. Moreover, the adaptive nature of our model brings a significant added value. Because for each country our model only selects the variables that are relevant to predict conflict intensity, the retained predictors can be analyzed to describe the dynamic configuration of conflict drivers both across countries and within countries over time. Countries can then be clustered to observe the emergence of broader patterns related to correlates of conflict. In this sense, our ap-proach produces interpretable forecasts, addressing one key limitation of contemporary ap-proaches to forecasting.