Forecasting Oil Market Volatility Using Machine Learning Models
Keywords:
oil market volatility, forecasting, machine learning, heteroskedasticity models, economic indicators, market fluctuationsAbstract
Forecasting oil market volatility is one of the major challenges in the global economy and financial markets, exerting broad impacts on the economic and strategic decisions of oil-producing and oil-consuming countries. This study was conducted with the aim of evaluating and forecasting oil market volatility using advanced machine learning models and analyzing the factors that influence fluctuations in oil prices. To this end, daily time-series data from macroeconomic and financial indicators—including the S&P 500 Index, the Dow Jones Index, the VIX Index, changes in unemployment claims (ICSA), and the interest rate (DGS10)—were collected and analyzed for the period from 2014 to 2024. In this research, heteroskedasticity models (GARCH and TGARCH) were first employed to extract conditional variance as a metric for volatility, and then these variables were used as inputs for machine learning models such as neural networks and random forests. The results indicated that machine learning models—especially threshold GARCH models with skewed Student-t and Johnson SU distributions—are capable of providing more accurate forecasts of oil market volatility. Moreover, variables such as stock market index volatility and the VIX Index have a positive and significant effect on oil market volatility. These findings demonstrate the effectiveness of machine learning models in analyzing the complex and nonlinear fluctuations of the oil market. The study suggests that, for improved oil market risk management, the use of machine learning models should receive greater attention, particularly during periods of market distress.
Downloads
References
1. Gupta N. Oil market and its impact on global economy. International journal of applied research. 2020;6:296-303.
2. Luciani G. The functioning of the international oil markets and its security implications. CEPS Working Documents. 2011. doi: 10.2139/ssrn.1898647.
3. Verleger PK. Adjusting to volatile energy prices: Peterson Institute; 1994.
4. Madhavi M, Nuttall WJ. Modern global oil market under stress: system dynamics and scenarios. Proceedings of the Institution of Civil Engineers-Energy. 2023;176(1):4-19. doi: 10.1680/jener.22.00020.
5. Yang T, Zhou F, Du M, Du Q, Zhou S. Fluctuation in the global oil market, stock market volatility, and economic policy uncertainty: A study of the US and China. The quarterly review of economics and finance. 2023;87:377-87. doi: 10.1016/j.qref.2021.08.006.
6. Salisu AA, Gupta R, Demirer R. Global financial cycle and the predictability of oil market volatility: Evidence from a GARCH-MIDAS model. Energy Economics. 2022;108:105934. doi: 10.1016/j.eneco.2022.105934.
7. Abdelsalam MAM. Oil price fluctuations and economic growth: The case of MENA countries. Review of Economics and Political Science. 2023;8(5):353-79. doi: 10.1108/REPS-12-2019-0162.
8. Gukasyan GL. Macroeconomic problems of the oil-exporting countries in the conditions of instability on the world market. RUDN Journal of Public Administration. 2018;5(4):411-25. doi: 10.22363/2312-8313-2018-5-4-411-425.
9. Turkeeva KA, Suleimenova AS. Factors and conditions of transformation of the world oil market. Economy: strategy and practice. 2021;16(2):71-85. doi: 10.51176/1997-9967-2021-2-71-85.
10. Moshiri S, Kheirandish E. Global impacts of oil price shocks: the trade effect. Journal of Economic Studies. 2024;51(1):126-44. doi: 10.1108/JES-08-2022-0455.
11. Islam U, Awwad EM, Sarhan NM, Fattah Sharaf MA, Ali I, Khan I, et al. Enhancing economic stability with innovative crude oil price prediction and policy uncertainty mitigation in USD energy stock markets. Fluctuation and Noise Letters. 2024;23(02):2440021. doi: 10.1142/S0219477524400212.
12. Alawadhi SA, Longe AE. Oil price fluctuation and their impact on the macroeconomic variables: The case of Kuwait. International Journal of Energy Economics and Policy. 2024;14(3):375-86. doi: 10.32479/ijeep.15713.
13. Oduyemi G, Owoeye T. Oil price fluctuation and health outcomes in an oil exporting country: Evidence from Nigeria. International Journal of Energy Economics and Policy. 2020;10(4):212-20. doi: 10.32479/ijeep.9266.
14. Hesami S, Rustamov B, Rjoub H, Wong WK. Implications of oil price fluctuations for tourism receipts: the case of oil exporting countries. Energies. 2020;13(17):4349. doi: 10.3390/en13174349.
15. Li X, Wei Y, Chen X, Ma F, Liang C, Chen W. Which uncertainty is powerful to forecast crude oil market volatility? New evidence. International Journal of Finance & Economics. 2022;27(4):4279-97. doi: 10.1002/ijfe.2371.
16. Akinfiev V. Global oil market forecasting models. IEEE; 2020. p. 1-5.
17. Norouzi N, Fani M. Black gold falls, black plague arise-An Opec crude oil price forecast using a gray prediction model. Upstream Oil and Gas Technology. 2020;5:100015. doi: 10.1016/j.upstre.2020.100015.
18. Liu S, Fang W, Gao X, Wang Z, An F, Wen S. Self-similar behaviors in the crude oil market. Energy. 2020;211:118682. doi: 10.1016/j.energy.2020.118682.
19. Xu Z, Mohsin M, Ullah K, Ma X. Using econometric and machine learning models to forecast crude oil prices: Insights from economic history. Resources Policy. 2023;83:103614. doi: 10.1016/j.resourpol.2023.103614.
20. Aunjum MR, Naqi M, Jamil S. A feedforward neural network model for forecasting crude oil prices using macroeconomic and geopolitical factors. IEEE; 2021. p. 1-6.
21. Swetha G, Vardhan NV, Bhavana S, Sirisha T, Nithish M. DEEP LEARNING-POWERED FORECASTING OF CRUDE OIL PRICES: CAPTURING NONLINEAR MARKET DYNAMICS. Scientific Digest : Journal of Applied Engineering. 2025;12(1):436-43. doi: 10.70864/joae.2024.v12.i1.pp436-443.
22. Fallah MF, Pourmansouri R, Ahmadpour B. Presenting a new deep learning-based method with the incorporation of error effects to predict certain cryptocurrencies. International Review of Financial Analysis. 2024;95:103466. doi: 10.1016/j.irfa.2024.103466.
23. Pourmansouri R, Birau R. Financial econometrics: Cambridge Scholars Publishing; 2024.
24. Pourmansouri R, Fallahshams M, Afshani RGG. Designing a financial stress index based on the GHARCH-DCC approach and machine learning models. Journal of the Knowledge Economy. 2025;16(1):2689-718. doi: 10.1007/s13132-024-02075-9.
Downloads
Published
Submitted
Revised
Accepted
Issue
Section
License
Copyright (c) 2025 Zahra Majdi (Author); Farhad Hanifi; Mirfaiz Fallah Shams (Author)
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
