Time-Varying Jump Intensity and Volatility Forecasting of Crude Oil Returns

Modelling and forecasting of crude oil volatility have been widely examined using GARCH-type models, and evidence suggests the presence of time-varying jumps in the crude oil market. This paper combines two time-varying jump intensities (State-dependent and Hawkes process) in the GARCH model to capture the jump dynamics and conditional variance of crude oil (WTI and Brent) returns and evaluate the role of jump intensity in forecasting crude oil price volatility. The in-sample and out-of-sample results show that the jump intensity as an explanatory variable can significantly improve the forecasting of WTI and Brent crude oil volatility. In the forecasting performance of WTI crude oil volatility, the more complex the jump intensity model, the better its forecasting power. However, in the forecasting performance of Brent crude oil price volatility, the results are not the same, but indicate that the non-linear characteristics of volatility provide more forecasting information. Further analysis shows that the Hawkes Jump Intensity (HJI)-GARCH model can improve the volatility forecasting performance significantly and consistently during the COVID-19 crisis period.