Forecasting Realized Volatility of the Oil Future Prices Via Machine Learning

30 Pages Posted: 24 Nov 2020 Last revised: 3 Aug 2021

See all articles by Byung-June Kim

Byung-June Kim

Pohang University of Science and Technology (POSTECH)

Taeyoon Kim

Pohang University of Science and Technology (POSTECH)

Bong-Gyu Jang

Pohang University of Science and Technology (POSTECH)

Date Written: October 8, 2020

Abstract

This paper explores the possibility of the potential usage of machine learning models in the field of realized volatility forecasting of crude oil with a vast variety of empirical analyses and robustness checks. Although the conventional heterogeneous autoregressive (HAR) model is widely accepted, it failed in out-of-sample recently. However, machine learning models with the HAR factors can improve forecasting performance significantly. The model confidence set test, Diebold-Mariano test, and Pesaran-Timmermann test support the empirical results statistically.

Keywords: volatility forecasting, oil future, machine learning, forecasting model

JEL Classification: C5, C22, G1, Q4

Suggested Citation

Kim, Byung-June and Kim, Taeyoon and Jang, Bong-Gyu, Forecasting Realized Volatility of the Oil Future Prices Via Machine Learning (October 8, 2020). Available at SSRN: https://ssrn.com/abstract=3708014 or http://dx.doi.org/10.2139/ssrn.3708014

Byung-June Kim

Pohang University of Science and Technology (POSTECH) ( email )

77 Cheongam-ro
Pohang
Korea, Republic of (South Korea)

Taeyoon Kim (Contact Author)

Pohang University of Science and Technology (POSTECH) ( email )

77 Cheongam-ro
Pohang
Korea, Republic of (South Korea)

Bong-Gyu Jang

Pohang University of Science and Technology (POSTECH) ( email )

77 Cheongam-ro
Pohang
Korea, Republic of (South Korea)

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
76
Abstract Views
357
rank
400,184
PlumX Metrics