IDEAS home Printed from https://ideas.repec.org/a/eee/riibaf/v66y2023ics0275531923001460.html
   My bibliography  Save this article

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 search for a different version of it.

    References listed on IDEAS

    as
    1. 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.
    2. 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.
    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. 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).

    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. 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.).
    2. Xing Zhang, 2018. "Short-Term Load Forecasting for Electric Bus Charging Stations Based on Fuzzy Clustering and Least Squares Support Vector Machine Optimized by Wolf Pack Algorithm," Energies, MDPI, vol. 11(6), pages 1-18, June.
    3. Zeng, Sheng & Su, Bin & Zhang, Minglong & Gao, Yuan & Liu, Jun & Luo, Song & Tao, Qingmei, 2021. "Analysis and forecast of China's energy consumption structure," Energy Policy, Elsevier, vol. 159(C).
    4. Houjian Li & Xinya Huang & Deheng Zhou & Andi Cao & Mengying Su & Yufeng Wang & Lili Guo, 2022. "Forecasting Carbon Price in China: A Multimodel Comparison," IJERPH, MDPI, vol. 19(10), pages 1-16, May.
    5. 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).
    6. Sun, Wei & Zhang, Chongchong, 2018. "Analysis and forecasting of the carbon price using multi—resolution singular value decomposition and extreme learning machine optimized by adaptive whale optimization algorithm," Applied Energy, Elsevier, vol. 231(C), pages 1354-1371.
    7. Song, Yazhi & Liu, Tiansen & Liang, Dapeng & Li, Yin & Song, Xiaoqiu, 2019. "A Fuzzy Stochastic Model for Carbon Price Prediction Under the Effect of Demand-related Policy in China's Carbon Market," Ecological Economics, Elsevier, vol. 157(C), pages 253-265.
    8. Shao, Liuguo & Zhang, Hua, 2020. "The impact of oil price on the clean energy metal prices: A multi-scale perspective," Resources Policy, Elsevier, vol. 68(C).
    9. Liu, Shuihan & Xie, Gang & Wang, Zhengzhong & Wang, Shouyang, 2024. "A secondary decomposition-ensemble framework for interval carbon price forecasting," Applied Energy, Elsevier, vol. 359(C).
    10. Juan Luis Martín-Ortega & Javier Chornet & Ioannis Sebos & Sander Akkermans & María José López Blanco, 2024. "Enhancing Transparency of Climate Efforts: MITICA’s Integrated Approach to Greenhouse Gas Mitigation," Sustainability, MDPI, vol. 16(10), pages 1-35, May.
    11. Huang, Wenyang & Wang, Huiwen & Qin, Haotong & Wei, Yigang & Chevallier, Julien, 2022. "Convolutional neural network forecasting of European Union allowances futures using a novel unconstrained transformation method," Energy Economics, Elsevier, vol. 110(C).
    12. Wang, Jujie & Zhuang, Zhenzhen & Gao, Dongming, 2023. "An enhanced hybrid model based on multiple influencing factors and divide-conquer strategy for carbon price prediction," Omega, Elsevier, vol. 120(C).
    13. Qingjie Zhou & Panpan Zhu & Yinpeng Zhang, 2023. "Contagion Spillover from Bitcoin to Carbon Futures Pricing: Perspective from Investor Attention," Energies, MDPI, vol. 16(2), pages 1-22, January.
    14. Yan, Kai & Zhang, Wei & Shen, Dehua, 2020. "Stylized facts of the carbon emission market in China," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 555(C).
    15. Ouyang, Zisheng & Lu, Min & Ouyang, Zhongzhe & Zhou, Xuewei & Wang, Ren, 2024. "A novel integrated method for improving the forecasting accuracy of crude oil: ESMD-CFastICA-BiLSTM-Attention," Energy Economics, Elsevier, vol. 138(C).
    16. E, Jianwei & Ye, Jimin & He, Lulu & Jin, Haihong, 2019. "Energy price prediction based on independent component analysis and gated recurrent unit neural network," Energy, Elsevier, vol. 189(C).
    17. Chen, Linfei & Zhao, Xuefeng, 2024. "A multiscale and multivariable differentiated learning for carbon price forecasting," Energy Economics, Elsevier, vol. 131(C).
    18. Wang, Minggang & Zhu, Mengrui & Tian, Lixin, 2022. "A novel framework for carbon price forecasting with uncertainties," Energy Economics, Elsevier, vol. 112(C).
    19. Xie, Qiwei & Hao, Jingjing & Li, Jingyu & Zheng, Xiaolong, 2022. "Carbon price prediction considering climate change: A text-based framework," Economic Analysis and Policy, Elsevier, vol. 74(C), pages 382-401.
    20. 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.

    More about this item

    Keywords

    LSTM; Attention; Prediction; Futures price; EU carbon market;
    All these 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.