Modelling and Forecasting Energy Market Volatility Using GARCH and Machine Learning Approach

TL;DR

This study compares GARCH and machine learning models for energy market volatility forecasting, finding machine learning models outperform traditional GARCH models and revealing transmission patterns among energy commodities.

Contribution

It provides a comprehensive comparison of GARCH and machine learning approaches using diverse variables and introduces SHAP analysis for volatility transmission insights.

Findings

Machine learning models outperform GARCH in forecasting accuracy.

GARCH models tend to overpredict, while machine learning models tend to underpredict volatility.

Volatility transmission occurs from crude oil to gasoline and heating oil markets.

Abstract

This paper presents a comparative analysis of univariate and multivariate GARCH-family models and machine learning algorithms in modeling and forecasting the volatility of major energy commodities: crude oil, gasoline, heating oil, and natural gas. It uses a comprehensive dataset incorporating financial, macroeconomic, and environmental variables to assess predictive performance and discusses volatility persistence and transmission across these commodities. Aspects of volatility persistence and transmission, traditionally examined by GARCH-class models, are jointly explored using the SHAP (Shapley Additive exPlanations) method. The findings reveal that machine learning models demonstrate superior out-of-sample forecasting performance compared to traditional GARCH models. Machine learning models tend to underpredict, while GARCH models tend to overpredict energy market volatility, suggesting a hybrid use of both types of models. There is volatility transmission from crude oil to the gasoline and heating oil markets. The volatility transmission in the natural gas market is less prevalent.