A Decision-Support Approach to International Natural Gas Price Forecasting Using Machine Learning Models

Peifeng Wu; Yaqiang Chen

doi:10.31181/dmame8220251519

Authors

Peifeng Wu Faculty of Statistics, Jilin University of Finance and Economics, Changchun 130000, Jilin, China
Yaqiang Chen Faculty of Statistics, Jilin University of Finance and Economics, Changchun 130000, Jilin, China

DOI:

https://doi.org/10.31181/dmame8220251519

Keywords:

Machine Learning Forecasting, Natural Gas Market Prices, Decision-Making in Energy Management, Predictive Analytics

Abstract

Accurate forecasting of international natural gas prices is essential for effective decision-making within the context of a volatile energy market, as unpredictable responses to price fluctuations often arise from non-stationary behaviour. Traditional econometric approaches frequently encounter limitations in capturing market volatility, nonlinear dynamics, and structural breaks, which diminishes their practical utility for strategic planning and operational decisions. This study seeks to conduct a comparative analysis of multiple machine learning (ML) techniques, including linear regression, support vector machines, decision trees, random forests, neural networks, and ensemble methods, in forecasting international natural gas prices using datasets obtained from the International Energy Agency (IEA), Global Data, and the Bloomberg terminal. The findings indicate that more sophisticated ML models, particularly ensemble methods and neural networks, outperform conventional forecasting approaches in terms of accuracy and reliability. Furthermore, the study highlights that forecasts generated through ML can significantly enhance decision-making processes for key stakeholders in the natural gas sector, including government policymakers, investors, and oil and gas producers, by informing structured risk management, optimising resource allocation, and supporting long-term strategic planning

Downloads

Download data is not yet available.

References

[1] Aczel, M. R. (2022). Technological revolution in natural gas developments and LNG: Policy advancements and their implications for national and international markets. In The Palgrave Handbook of Natural Gas and Global Energy Transitions (pp. 21-72). Springer. https://doi.org/10.1007/978-3-030-91566-7_2

[2] Agency, T. I. E. (2024). The International Energy Agency. https://www.iea.org/data-and-statistics/data-product/natural-gas-information

[3] Becha, M., Dridi, O., Riabi, O., & Benmessaoud, Y. (2020). Use of machine learning techniques in financial forecasting. 2020 International Multi-Conference on:“Organization of Knowledge and Advanced Technologies”(OCTA), 1728164036. https://doi.org/10.1109/OCTA49274.2020.9151854

[4] Biau, G., & Scornet, E. (2016). A random forest guided tour. Test, 25(2), 197-227. https://doi.org/10.1007/s11749-016-0481-7

[5] Bloomberg. (2024). Bloomberg Terminal. https://www.investing.com/indices/bloomberg-natural-gas-historical-data

[6] Bouazizi, T., Abid, I., Guesmi, K., & Makrychoriti, P. (2024). Evolving energies: Analyzing stability amidst recent challenges in the natural gas market. International Review of Financial Analysis, 95, 103346. https://doi.org/10.1016/j.irfa.2024.103346

[7] Brynjolfsson, E., & McElheran, K. (2016). The rapid adoption of data-driven decision-making. American Economic Review, 106(5), 133-139. https://doi.org/10.1257/aer.p20161016

[8] Caiado, J., & Crato, N. (2007). A GARCH-based method for clustering of financial time series: International stock markets evidence. In Recent advances in stochastic modeling and data analysis (pp. 542-551). World Scientific. https://doi.org/10.1142/6568

[9] Chen, T., & Guestrin, C. (2016). Xgboost: A scalable tree boosting system. Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining, 785-794. https://doi.org/10.1145/2939672.2939785

[10] Dodevski, A., Koceska, N., & Koceski, S. (2018). Stock Movement Prediction Based on Social Media Sentiment Analysis. Journal of Applied Economics and Business. http://www.aebjournal.org/article060303.php

[11] Han, T., Jiang, D., Zhao, Q., Wang, L., & Yin, K. (2018). Comparison of random forest, artificial neural networks and support vector machine for intelligent diagnosis of rotating machinery. Transactions of the Institute of Measurement and Control, 40(8), 2681-2693. https://doi.org/10.1177/0142331217708242

[12] Hastie, T., Tibshirani, R., & Friedman, J. (2009). The elements of statistical learning. In: Springer series in statistics New-York. https://www.sas.upenn.edu/~fdiebold/NoHesitations/BookAdvanced.pdf

[13] Heaton, J. B., Polson, N. G., & Witte, J. H. (2017). Deep learning for finance: deep portfolios. Applied Stochastic Models in Business and Industry, 33(1), 3-12. https://doi.org/10.1002/asmb.2209

[14] Hepşen, A., & Vatansever, M. (2011). Forecasting future trends in Dubai housing market by using Box‐Jenkins autoregressive integrated moving average. International Journal of Housing Markets and Analysis, 4(3), 210-223. https://doi.org/10.1108/17538271111153004

[15] Htun, H. H., Biehl, M., & Petkov, N. (2023). Survey of feature selection and extraction techniques for stock market prediction. Financial Innovation, 9(1), 26. https://doi.org/10.1186/s40854-022-00441-7

[16] Jammazi, R., & Aloui, C. (2012). Crude oil price forecasting: Experimental evidence from wavelet decomposition and neural network modeling. Energy Economics, 34(3), 828-841. https://doi.org/10.1016/j.eneco.2011.07.018

[17] Jiang, Z., Xu, D., & Liang, J. (2017). A deep reinforcement learning framework for the financial portfolio management problem. arXiv preprint arXiv:1706.10059. https://doi.org/10.48550/arXiv.1706.10059

[18] Jie, Y., Rasool, Z., Nassani, A. A., Mattayaphutron, S., & Murad, M. (2024). Sustainable Central Asia: Impact of fintech, natural resources, renewable energy, and financial inclusion to combat environmental degradation and achieving sustainable development goals. Resources Policy, 95, 105138. https://doi.org/10.1016/j.resourpol.2024.105138

[19] Kemfert, C., Präger, F., Braunger, I., Hoffart, F. M., & Brauers, H. (2022). The expansion of natural gas infrastructure puts energy transitions at risk. Nature Energy, 7(7), 582-587. https://doi.org/10.1038/s41560-022-01060-3

[20] Kim, K.-j. (2003). Financial time series forecasting using support vector machines. Neurocomputing, 55(1-2), 307-319. https://doi.org/10.1016/S0925-2312(03)00372-2

[21] Litvinenko, V. (2020). The role of hydrocarbons in the global energy agenda: The focus on liquefied natural gas. Resources, 9(5), 59. https://doi.org/10.3390/resources9050059

[22] Liu, Z., Zhu, Z., Gao, J., & Xu, C. (2021). Forecast methods for time series data: A survey. Ieee Access, 9, 91896-91912. https://doi.org/10.1109/ACCESS.2021.3091162

[23] Namany, S., Al-Ansari, T., & Govindan, R. (2019). Sustainable energy, water and food nexus systems: A focused review of decision-making tools for efficient resource management and governance. Journal of Cleaner Production, 225, 610-626. https://doi.org/10.1016/j.jclepro.2019.03.304

[24] Spiliotis, E., Makridakis, S., Kaltsounis, A., & Assimakopoulos, V. (2021). Product sales probabilistic forecasting: An empirical evaluation using the M5 competition data. International Journal of Production Economics, 240, 108237. https://doi.org/10.1016/j.ijpe.2021.108237

[25] Su, M., Zhang, Z., Zhu, Y., & Zha, D. (2019). Data-driven natural gas spot price forecasting with least squares regression boosting algorithm. Energies, 12(6), 1094. https://doi.org/10.3390/en12061094

[26] Sweeney, C., Bessa, R. J., Browell, J., & Pinson, P. (2020). The future of forecasting for renewable energy. Wiley Interdisciplinary Reviews: Energy and Environment, 9(2), e365. https://doi.org/10.1002/wene.365

[27] Ticknor, J. L. (2013). A Bayesian regularized artificial neural network for stock market forecasting. Expert systems with applications, 40(14), 5501-5506. https://doi.org/10.1016/j.eswa.2013.04.013

[28] Tiwari, A. K., Sharma, G. D., Rao, A., Hossain, M. R., & Dev, D. (2024). Unraveling the crystal ball: Machine learning models for crude oil and natural gas volatility forecasting. Energy Economics, 134, 107608. https://doi.org/10.1016/j.eneco.2024.107608

[29] Ullah, F., Nadeem, M., Abrar, M., Amin, F., Salam, A., & Khan, S. (2023). Enhancing brain tumor segmentation accuracy through scalable federated learning with advanced data privacy and security measures. Mathematics, 11(19), 4189. https://doi.org/10.3390/math11194189

[30] Ullah, F., Salam, A., Abrar, M., Ahmad, M., Ullah, F., Khan, A., Alharbi, A., & Alosaimi, W. (2022). Machine health surveillance system by using deep learning sparse autoencoder. Soft Computing, 26(16), 7737-7750. https://doi.org/10.1007/s00500-022-06755-z

[31] Yağlı, İ., & Haykır, Ö. (2023). Investor Happiness And Cryptocurrency Returns: Fresh Evidence From Top Five Cryptocurrencies. Pamukkale Üniversitesi Sosyal Bilimler Enstitüsü Dergisi(59), 293-305. https://doi.org/10.30794/pausbed.1183813

[32] Zhang, W.-B. (1991). Synergetic Economics. Springer Series in Synergetics. https://doi.org/10.1007/978-3-642-75909-3