IDEAS home Printed from https://ideas.repec.org/a/eee/riibaf/v66y2023ics0275531923001460.html

Exploring the predictability of attention mechanism with LSTM: Evidence from EU carbon futures prices

Author

Listed:
  • Duan, Kun
  • Wang, Rui
  • Chen, Shun
  • Ge, Lei

Abstract

This paper forecasts the price dynamics of carbon futures in the form of return under the EU emission trading scheme by using an attention mechanism based long short-term memory (AttLSTM) neural network. Prediction of the carbon price dynamics exploits not only historical information of itself but also that of its key predictors, including the price dynamics in fossil energy and stock markets. We find that the attention mechanism can significantly improve the LSTM prediction for the carbon price dynamics. The superior predictability of AttLSTM is examined by its lower MSE, MAE, and RMSE values in the out-of-sample forecasting against a standard LSTM prediction both in various parameter settings and tuning experiments, respectively. This is further demonstrated by the Wilcoxon signed rank test and Diebold Marian test. Our results reveal strong predictive performance of the AttLSTM for the carbon futures price dynamics, and corresponding implications should be of interest to various stakeholders.

Suggested Citation

  • Duan, Kun & Wang, Rui & Chen, Shun & Ge, Lei, 2023. "Exploring the predictability of attention mechanism with LSTM: Evidence from EU carbon futures prices," Research in International Business and Finance, Elsevier, vol. 66(C).
    • Handle: RePEc:eee:riibaf:v:66:y:2023:i:c:s0275531923001460
    DOI: 10.1016/j.ribaf.2023.102020
    as

    Download full text from publisher

    File URL: http://www.sciencedirect.com/science/article/pii/S0275531923001460
    Download Restriction: Full text for ScienceDirect subscribers only
    File URL: https://libkey.io/10.1016/j.ribaf.2023.102020?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    As the access to this document is restricted, you may want to

    for a different version of it.

    References listed on IDEAS

    as
    1. Niu, Zhewen & Yu, Zeyuan & Tang, Wenhu & Wu, Qinghua & Reformat, Marek, 2020. "Wind power forecasting using attention-based gated recurrent unit network," Energy, Elsevier, vol. 196(C).
    2. Bou-Hamad, Imad & Jamali, Ibrahim, 2020. "Forecasting financial time-series using data mining models: A simulation study," Research in International Business and Finance, Elsevier, vol. 51(C).
    3. Goodell, John W. & Nammouri, Hela & Saâdaoui, Foued & Ben Jabeur, Sami, 2023. "Carbon allowances amid climate change concerns: Fresh insights from wavelet multiscale analysis," Finance Research Letters, Elsevier, vol. 55(PA).
    4. Ren, Xiaohang & Duan, Kun & Tao, Lizhu & Shi, Yukun & Yan, Cheng, 2022. "Carbon prices forecasting in quantiles," Energy Economics, Elsevier, vol. 108(C).
    5. Chevallier, Julien, 2011. "A model of carbon price interactions with macroeconomic and energy dynamics," Energy Economics, Elsevier, vol. 33(6), pages 1295-1312.
    6. Paolella, Marc S. & Taschini, Luca, 2008. "An econometric analysis of emission allowance prices," Journal of Banking & Finance, Elsevier, vol. 32(10), pages 2022-2032, October.
    7. Zhu, Bangzhu & Han, Dong & Wang, Ping & Wu, Zhanchi & Zhang, Tao & Wei, Yi-Ming, 2017. "Forecasting carbon price using empirical mode decomposition and evolutionary least squares support vector regression," Applied Energy, Elsevier, vol. 191(C), pages 521-530.
    8. repec:dau:papers:123456789/6969 is not listed on IDEAS
    9. Charalampos Stasinakis & Georgios Sermpinis & Ioannis Psaradellis & Thanos Verousis, 2016. "Krill-Herd Support Vector Regression and heterogeneous autoregressive leverage: evidence from forecasting and trading commodities," Quantitative Finance, Taylor & Francis Journals, vol. 16(12), pages 1901-1915, December.
    10. Yixuan Li & Charalampos Stasinakis & Wee Meng Yeo, 2022. "A Hybrid XGBoost-MLP Model for Credit Risk Assessment on Digital Supply Chain Finance," Forecasting, MDPI, vol. 4(1), pages 1-24, January.
    11. Sermpinis, Georgios & Stasinakis, Charalampos & Hassanniakalager, Arman, 2017. "Reverse adaptive krill herd locally weighted support vector regression for forecasting and trading exchange traded funds," European Journal of Operational Research, Elsevier, vol. 263(2), pages 540-558.
    12. Ser-Huang Poon & Clive W.J. Granger, 2003. "Forecasting Volatility in Financial Markets: A Review," Journal of Economic Literature, American Economic Association, vol. 41(2), pages 478-539, June.
    13. Hammoudeh, Shawkat & Nguyen, Duc Khuong & Sousa, Ricardo M., 2014. "What explain the short-term dynamics of the prices of CO2 emissions?," Energy Economics, Elsevier, vol. 46(C), pages 122-135.
    14. Duan, Kun & Ren, Xiaohang & Shi, Yukun & Mishra, Tapas & Yan, Cheng, 2021. "The marginal impacts of energy prices on carbon price variations: Evidence from a quantile-on-quantile approach," Energy Economics, Elsevier, vol. 95(C).
    15. Dbouk, Wassim & Jamali, Ibrahim, 2018. "Predicting daily oil prices: Linear and non-linear models," Research in International Business and Finance, Elsevier, vol. 46(C), pages 149-165.
    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. Yin, Hao & Yin, Yiding & Li, Hanhong & Zhu, Jianbin & Xian, Zikang & Tang, Yanshu & Xiao, Liexi & Rong, Jiayu & Li, Chen & Zhang, Haitao & Xie, Zhifeng & Meng, Anbo, 2025. "Carbon emissions trading price forecasting based on temporal-spatial multidimensional collaborative attention network and segment imbalance regression," Applied Energy, Elsevier, vol. 377(PA).
    2. Xue, Jianhao & Dai, Xingyu & Xiao, Ling & Wang, Qunwei & Li, Matthew C., 2025. "Multi-objective carbon-energy portfolio optimization under investment horizon heterogeneity," Research in International Business and Finance, Elsevier, vol. 79(C).
    3. Xing Zhou & Jianze Xu & Ming Zhang & Anyi Niu & Chuxia Lin, 2025. "Gaps between market performance, government planning and social objectives: projections and comparisons of carbon price intervals," Humanities and Social Sciences Communications, Palgrave Macmillan, vol. 12(1), pages 1-20, December.
    4. Chen, Rui & Jiang, Haiqi & Guo, Tingyu & Fan, Chenyou, 2025. "Can Large Language Models forecast carbon price movements? Evidence from Chinese carbon markets," Research in International Business and Finance, Elsevier, vol. 77(PB).
    5. Chang, Chunyuan & Li, Liming, 2025. "Wood-based panel futures price prediction incorporating supply chain features," Forest Policy and Economics, Elsevier, vol. 176(C).
    6. Tian, Yingjie & Wen, Haonan & Guo, Kun, 2025. "Machine learning applications in climate finance: An overview," Research in International Business and Finance, Elsevier, vol. 79(C).
    7. Su, Miao & Nie, Yufei & Li, Jiankun & Yang, Lin & Kim, Woohyoung, 2024. "Futures markets and the baltic dry index: A prediction study based on deep learning," Research in International Business and Finance, Elsevier, vol. 71(C).
    8. Huang, Jianying & Yuee, Gao & Li, Chengjiang & Yu, Xiaoqing & Xiong, Wei, 2026. "A hybrid attention-enabled multivariate information fusion for carbon price forecasting," Renewable Energy, Elsevier, vol. 256(PE).
    9. Yang, Kun & Sun, Yuying & Hong, Yongmiao & Wang, Shouyang, 2024. "Forecasting interval carbon price through a multi-scale interval-valued decomposition ensemble approach," Energy Economics, Elsevier, vol. 139(C).

    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. Chen, Linfei & Zhao, Xuefeng, 2024. "A multiscale and multivariable differentiated learning for carbon price forecasting," Energy Economics, Elsevier, vol. 131(C).
    2. Lei, Heng & Xue, Minggao & Liu, Huiling, 2022. "Probability distribution forecasting of carbon allowance prices: A hybrid model considering multiple influencing factors," Energy Economics, Elsevier, vol. 113(C).
    3. Lovcha, Yuliya & Perez-Laborda, Alejandro & Sikora, Iryna, 2022. "The determinants of CO2 prices in the EU emission trading system," Applied Energy, Elsevier, vol. 305(C).
    4. Huang, Wenyang & Zhao, Jianyu & Wang, Xiaokang, 2024. "Model-driven multimodal LSTM-CNN for unbiased structural forecasting of European Union allowances open-high-low-close price," Energy Economics, Elsevier, vol. 132(C).
    5. Chen, Weidong & Xiong, Shi & Chen, Quanyu, 2022. "Characterizing the dynamic evolutionary behavior of multivariate price movement fluctuation in the carbon-fuel energy markets system from complex network perspective," Energy, Elsevier, vol. 239(PA).
    6. Huang, Yumeng & Dai, Xingyu & Wang, Qunwei & Zhou, Dequn, 2021. "A hybrid model for carbon price forecastingusing GARCH and long short-term memory network," Applied Energy, Elsevier, vol. 285(C).
    7. Han, Meng & Ding, Lili & Zhao, Xin & Kang, Wanglin, 2019. "Forecasting carbon prices in the Shenzhen market, China: The role of mixed-frequency factors," Energy, Elsevier, vol. 171(C), pages 69-76.
    8. Liu, Shuihan & Li, Mingchen & Yang, Kun & Wei, Yunjie & Wang, Shouyang, 2025. "From forecasting to trading: A multimodal-data-driven approach to reversing carbon market losses," Energy Economics, Elsevier, vol. 144(C).
    9. Tan, Xueping & Sirichand, Kavita & Vivian, Andrew & Wang, Xinyu, 2022. "Forecasting European carbon returns using dimension reduction techniques: Commodity versus financial fundamentals," International Journal of Forecasting, Elsevier, vol. 38(3), pages 944-969.
    10. Xu, Yingying & Dai, Yifan & Guo, Lingling & Chen, Jingjing, 2024. "Leveraging machine learning to forecast carbon returns: Factors from energy markets," Applied Energy, Elsevier, vol. 357(C).
    11. Lovcha, Yuliya & Pérez Laborda, Àlex & Sikora, Iryna, 2019. "The Determinants of CO2 prices in the EU ETS System," Working Papers 2072/376031, Universitat Rovira i Virgili, Department of Economics.
    12. Wei Jiang & Jingang Jiang & Sonia Chien-I Chen, 2025. "Untangling Carbon–Clean Energy Dynamics: A Quantile Granger-Causality Perspective," Sustainability, MDPI, vol. 17(7), pages 1-20, April.
    13. Zhao, Xin & Han, Meng & Ding, Lili & Kang, Wanglin, 2018. "Usefulness of economic and energy data at different frequencies for carbon price forecasting in the EU ETS," Applied Energy, Elsevier, vol. 216(C), pages 132-141.
    14. Gil-Alana, Luis A. & Gupta, Rangan & de Gracia, Fernando Perez, 2016. "Modeling persistence of carbon emission allowance prices," Renewable and Sustainable Energy Reviews, Elsevier, vol. 55(C), pages 221-226.
    15. Duan, Kun & Ren, Xiaohang & Shi, Yukun & Mishra, Tapas & Yan, Cheng, 2021. "The marginal impacts of energy prices on carbon price variations: Evidence from a quantile-on-quantile approach," Energy Economics, Elsevier, vol. 95(C).
    16. Xiaohan Cai & Bo Yan, 2025. "Tail Dependence of Liquidity and Volatility in Carbon Futures Market: Evidence From EU ETS," Managerial and Decision Economics, John Wiley & Sons, Ltd., vol. 46(6), pages 3538-3570, September.
    17. Wang, Jiqian & Guo, Xiaozhu & Tan, Xueping & Chevallier, Julien & Ma, Feng, 2023. "Which exogenous driver is informative in forecasting European carbon volatility: Bond, commodity, stock or uncertainty?," Energy Economics, Elsevier, vol. 117(C).
    18. Ren, Xiaohang & Duan, Kun & Tao, Lizhu & Shi, Yukun & Yan, Cheng, 2022. "Carbon prices forecasting in quantiles," Energy Economics, Elsevier, vol. 108(C).
    19. Elsayed, Ahmed H. & Khalfaoui, Rabeh & Zhang, Dongna & Urquhart, Andrew, 2025. "AI and carbon pricing in turbulent times: Navigating market dynamics for a sustainable future," International Review of Financial Analysis, Elsevier, vol. 107(C).
    20. Gary S. Anderson & Alena Audzeyeva, 2019. "A Coherent Framework for Predicting Emerging Market Credit Spreads with Support Vector Regression," Finance and Economics Discussion Series 2019-074, Board of Governors of the Federal Reserve System (U.S.).

    More about this item

    Keywords

    ;
    ;
    ;
    ;
    ;

    JEL classification:

    • C45 - Mathematical and Quantitative Methods - - Econometric and Statistical Methods: Special Topics - - - Neural Networks and Related Topics
    • C53 - Mathematical and Quantitative Methods - - Econometric Modeling - - - Forecasting and Prediction Models; Simulation Methods
    • G17 - Financial Economics - - General Financial Markets - - - Financial Forecasting and Simulation
    • Q50 - Agricultural and Natural Resource Economics; Environmental and Ecological Economics - - Environmental Economics - - - General

    Statistics

    Access and download statistics

    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:eee:riibaf:v:66:y:2023:i:c:s0275531923001460. 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: Catherine Liu (email available below). General contact details of provider: http://www.elsevier.com/locate/ribaf .

    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.