Do Geopolitical Risks Affect Volatility Forecasts for Crude Oil Futures? A Regime Switching Approach

This paper investigates whether geopolitical risks (GPRs) contains incremental information content to predict crude oil futures volatility under high-frequency Heterogeneous Autoregressive (HAR) model specifications. Moreover, considering structural breaks in crude oil volatility, we extend the HAR-type models with regime switching considerations. We find that geopolitical risks provides additional information for forecasting the realized volatility of crude oil futures. Further analysis results show that geopolitical acts (GPAs) has an important ability to predict future oil volatility in the short- and medium-terms, while GPRs has significant predictive power for the future long-term oil volatility. Furthermore, regime switching specifications can significantly improve the model's ability to predict volatility over relatively long horizons, and geopolitical indicators affect crude oil volatility in opposite directions under different regimes. In summary, our findings suggest that geopolitical risks and regime-switching specifications have a significant positive impact on the volatility prediction of the crude oil futures market and help improve performances of the HAR-type models