IDEAS home Printed from https://ideas.repec.org/a/gam/jeners/v14y2021i18p5782-d634984.html
   My bibliography  Save this article

Forecasting Natural Gas Spot Prices with Machine Learning

Author

Listed:
  • Dimitrios Mouchtaris

    (Faculty of Sciences, Aristotle University of Thessaloniki, 54124 Thessaloniki, Greece)

  • Emmanouil Sofianos

    (Department of Economics, Democritus University of Thrace, 69100 Komotini, Greece)

  • Periklis Gogas

    (Department of Economics, Democritus University of Thrace, 69100 Komotini, Greece)

  • Theophilos Papadimitriou

    (Department of Economics, Democritus University of Thrace, 69100 Komotini, Greece)

Abstract

The ability to accurately forecast the spot price of natural gas benefits stakeholders and is a valuable tool for all market participants in the competitive gas market. In this paper, we attempt to forecast the natural gas spot price 1, 3, 5, and 10 days ahead using machine learning methods: support vector machines (SVM), regression trees, linear regression, Gaussian process regression (GPR), and ensemble of trees. These models are trained with a set of 21 explanatory variables in a 5-fold cross-validation scheme with 90% of the dataset used for training and the remaining 10% used for testing the out-of-sample generalization ability. The results show that these machine learning methods all have different forecasting accuracy for every time frame when it comes to forecasting natural gas spot prices. However, the bagged trees (belonging to the ensemble of trees method) and the linear SVM models have superior forecasting performance compared to the rest of the models.

Suggested Citation

  • Dimitrios Mouchtaris & Emmanouil Sofianos & Periklis Gogas & Theophilos Papadimitriou, 2021. "Forecasting Natural Gas Spot Prices with Machine Learning," Energies, MDPI, vol. 14(18), pages 1-13, September.
    • Handle: RePEc:gam:jeners:v:14:y:2021:i:18:p:5782-:d:634984
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/1996-1073/14/18/5782/pdf
    Download Restriction: no
    File URL: https://www.mdpi.com/1996-1073/14/18/5782/
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Moting Su & Zongyi Zhang & Ye Zhu & Donglan Zha & Wenying Wen, 2019. "Data Driven Natural Gas Spot Price Prediction Models Using Machine Learning Methods," Energies, MDPI, vol. 12(9), pages 1-17, May.
    2. Jean Gaston Tamba & Salom Ndjakomo Essiane & Emmanuel Flavian Sapnken & Francis Djanna Koffi & Jean Luc Nsouand l & Bozidar Soldo & Donatien Njomo, 2018. "Forecasting Natural Gas: A Literature Survey," International Journal of Energy Economics and Policy, Econjournals, vol. 8(3), pages 216-249.
    3. Nguyen, Hang T. & Nabney, Ian T., 2010. "Short-term electricity demand and gas price forecasts using wavelet transforms and adaptive models," Energy, Elsevier, vol. 35(9), pages 3674-3685.
    4. Dragomirescu-Gaina, Catalin & Galariotis, Emilios & Philippas, Dionisis, 2021. "Chasing the ‘green bandwagon’ in times of uncertainty," Energy Policy, Elsevier, vol. 151(C).
    5. Gogas, Periklis & Papadimitriou, Theophilos & Sofianos, Emmanouil, 2019. "Money Neutrality, Monetary Aggregates and Machine Learning," DUTH Research Papers in Economics 4-2016, Democritus University of Thrace, Department of Economics.
    6. Buchanan, W. K. & Hodges, P. & Theis, J., 2001. "Which way the natural gas price: an attempt to predict the direction of natural gas spot price movements using trader positions," Energy Economics, Elsevier, vol. 23(3), pages 279-293, May.
    7. Wenting Zhang & Shigeyuki Hamori, 2020. "Do Machine Learning Techniques and Dynamic Methods Help Forecast US Natural Gas Crises?," Energies, MDPI, vol. 13(9), pages 1-22, May.
    8. Wang, Jun & Cao, Junxing & Yuan, Shan & Cheng, Ming, 2021. "Short-term forecasting of natural gas prices by using a novel hybrid method based on a combination of the CEEMDAN-SE-and the PSO-ALS-optimized GRU network," Energy, Elsevier, vol. 233(C).
    9. Herrera, Gabriel Paes & Constantino, Michel & Tabak, Benjamin Miranda & Pistori, Hemerson & Su, Jen-Je & Naranpanawa, Athula, 2019. "Long-term forecast of energy commodities price using machine learning," Energy, Elsevier, vol. 179(C), pages 214-221.
    10. Mishra, Vinod & Smyth, Russell, 2016. "Are natural gas spot and futures prices predictable?," Economic Modelling, Elsevier, vol. 54(C), pages 178-186.
    Full references (including those not matched with items on IDEAS)

    Citations

    Citations are extracted by the CitEc Project, subscribe to its RSS feed for this item.
    as


    Cited by:

    1. Renchu Guan & Aoqing Wang & Yanchun Liang & Jiasheng Fu & Xiaosong Han, 2022. "International Natural Gas Price Trends Prediction with Historical Prices and Related News," Energies, MDPI, vol. 15(10), pages 1-14, May.
    2. Sun-Feel Yang & So-Won Choi & Eul-Bum Lee, 2023. "A Prediction Model for Spot LNG Prices Based on Machine Learning Algorithms to Reduce Fluctuation Risks in Purchasing Prices," Energies, MDPI, vol. 16(11), pages 1-39, May.
    3. Yadong Pei & Chiou-Jye Huang & Yamin Shen & Mingyue Wang, 2023. "A Novel Model for Spot Price Forecast of Natural Gas Based on Temporal Convolutional Network," Energies, MDPI, vol. 16(5), pages 1-15, February.
    4. Periklis Gogas & Theophilos Papadimitriou, 2022. "Emerging Trends in Energy Economics," Energies, MDPI, vol. 15(14), pages 1-2, July.

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Xie, Gang & Jiang, Fuxin & Zhang, Chengyuan, 2023. "A secondary decomposition-ensemble methodology for forecasting natural gas prices using multisource data," Resources Policy, Elsevier, vol. 85(PA).
    2. Qin Lu & Jingwen Liao & Kechi Chen & Yanhui Liang & Yu Lin, 2024. "Predicting Natural Gas Prices Based on a Novel Hybrid Model with Variational Mode Decomposition," Computational Economics, Springer;Society for Computational Economics, vol. 63(2), pages 639-678, February.
    3. Yadong Pei & Chiou-Jye Huang & Yamin Shen & Mingyue Wang, 2023. "A Novel Model for Spot Price Forecast of Natural Gas Based on Temporal Convolutional Network," Energies, MDPI, vol. 16(5), pages 1-15, February.
    4. Gao, Shen & Hou, Chenghan & Nguyen, Bao H., 2021. "Forecasting natural gas prices using highly flexible time-varying parameter models," Economic Modelling, Elsevier, vol. 105(C).
    5. Jonathan Berrisch & Florian Ziel, 2022. "Distributional modeling and forecasting of natural gas prices," Journal of Forecasting, John Wiley & Sons, Ltd., vol. 41(6), pages 1065-1086, September.
    6. Gao, Shen & Hou, Chenghan & Nguyen, Bao H., 2020. "Forecasting natural gas prices using highly flexible time-varying parameter models," Working Papers 2020-01, University of Tasmania, Tasmanian School of Business and Economics.
    7. Laura Böhm & Sebastian Kolb & Thomas Plankenbühler & Jonas Miederer & Simon Markthaler & Jürgen Karl, 2023. "Short-Term Natural Gas and Carbon Price Forecasting Using Artificial Neural Networks," Energies, MDPI, vol. 16(18), pages 1-25, September.
    8. Moting Su & Zongyi Zhang & Ye Zhu & Donglan Zha, 2019. "Data-Driven Natural Gas Spot Price Forecasting with Least Squares Regression Boosting Algorithm," Energies, MDPI, vol. 12(6), pages 1-13, March.
    9. Wang, Jun & Cao, Junxing & Yuan, Shan & Cheng, Ming, 2021. "Short-term forecasting of natural gas prices by using a novel hybrid method based on a combination of the CEEMDAN-SE-and the PSO-ALS-optimized GRU network," Energy, Elsevier, vol. 233(C).
    10. Jonathan Berrisch & Florian Ziel, 2020. "Distributional Modeling and Forecasting of Natural Gas Prices," Papers 2010.06227, arXiv.org, revised Aug 2021.
    11. Drachal, Krzysztof, 2021. "Forecasting selected energy commodities prices with Bayesian dynamic finite mixtures," Energy Economics, Elsevier, vol. 99(C).
    12. Faramarz Saghi & Mustafa Jahangoshai Rezaee, 2023. "Integrating Wavelet Decomposition and Fuzzy Transformation for Improving the Accuracy of Forecasting Crude Oil Price," Computational Economics, Springer;Society for Computational Economics, vol. 61(2), pages 559-591, February.
    13. Feng, Zongbao & Wu, Xianguo & Chen, Hongyu & Qin, Yawei & Zhang, Limao & Skibniewski, Miroslaw J., 2022. "An energy performance contracting parameter optimization method based on the response surface method: A case study of a metro in China," Energy, Elsevier, vol. 248(C).
    14. Pinto, T. & Morais, H. & Oliveira, P. & Vale, Z. & Praça, I. & Ramos, C., 2011. "A new approach for multi-agent coalition formation and management in the scope of electricity markets," Energy, Elsevier, vol. 36(8), pages 5004-5015.
    15. Jammazi, Rania, 2012. "Oil shock transmission to stock market returns: Wavelet-multivariate Markov switching GARCH approach," Energy, Elsevier, vol. 37(1), pages 430-454.
    16. Zhao, Shuchun & Guo, Junheng & Dang, Xiuhu & Ai, Bingyan & Zhang, Minqing & Li, Wei & Zhang, Jinli, 2022. "Energy consumption, flow characteristics and energy-efficient design of cup-shape blade stirred tank reactors: Computational fluid dynamics and artificial neural network investigation," Energy, Elsevier, vol. 240(C).
    17. Liang, Chao & Xia, Zhenglan & Lai, Xiaodong & Wang, Lu, 2022. "Natural gas volatility prediction: Fresh evidence from extreme weather and extended GARCH-MIDAS-ES model," Energy Economics, Elsevier, vol. 116(C).
    18. Husain, Shaiara & Sohag, Kazi & Wu, Yanrui, 2022. "The response of green energy and technology investment to climate policy uncertainty: An application of twin transitions strategy," Technology in Society, Elsevier, vol. 71(C).
    19. Sofia Dahlgren & Jonas Ammenberg, 2021. "Sustainability Assessment of Public Transport, Part II—Applying a Multi-Criteria Assessment Method to Compare Different Bus Technologies," Sustainability, MDPI, vol. 13(3), pages 1-30, January.
    20. Abdulelah Alkesaiberi & Fouzi Harrou & Ying Sun, 2022. "Efficient Wind Power Prediction Using Machine Learning Methods: A Comparative Study," Energies, MDPI, vol. 15(7), pages 1-24, March.

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:gam:jeners:v:14:y:2021:i:18:p:5782-:d:634984. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: MDPI Indexing Manager (email available below). General contact details of provider: https://www.mdpi.com .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.