Geopolitics, Geoeconomics and Risk: A Machine Learning Approach

This paper studies how geopolitical and geoeconomic shocks transmit to sovereign risk. Using a daily panel of CDS spreads, financial variables, and news-based indicators for 42 advanced and emerging economies over 2018-2025, we estimate nonlinear Machine Learning models that capture the interactions and threshold effects through which these shocks operate. A Shapley-Taylor decomposition exactly partitions predicted spreads into four channels: Direct, Global Financial Cycle, Uncertainty, and Local. The decomposition reveals a structural distinction. Geopolitical shocks enter through the Direct channel -- repricing default probability -- with the global financial cycle providing a transient offset. Geoeconomic uncertainty shocks bypass the Direct channel and operate through expected monetary policy and risk appetite. Gravity regressions show geopolitical transmission decays with distance; policy-uncertainty shocks activate the Uncertainty channel globally. The taxonomy implies that liquidity provision can address financial-cycle-mediated transmission but not the persistent component of geopolitical risk premia.