Hybrid Machine Learning Analysis of Exogenous Features in China’s Guangdong Carbon Market Price Prediction
Main Article Content
Abstract
Carbon pricing is essential for the effective functioning of carbon markets, providing a basis for strategies that support sustainable green economic development. This study investigates the predictive power of intraday carbon price-related information, trading volume and crude oil prices within a hybrid model combining a convolutional neural network (CNN) and a long short-term memory (LSTM) network to forecast carbon emission allowance closing prices. The model is applied to Guangdong, China’s largest and most active carbon-trading market, to improve forecasting accuracy. The CNNLSTM models are benchmarked against a standalone LSTM model using multiple loss functions, with results showing the hybrid model’s clear superiority in both in-sample and out-of-sample forecasts. Analysis of exogenous variable highlights that lagged intraday opening, highest, lowest and closing (OHLC) prices are the most critical predictors, with their exclusion significantly reducing accuracy. Brent crude oil prices and trading volume provide moderate contributions to the model, while quasi-likelihood analysis reaffirms lagged OHLC information and oil prices as key factors in carbon price prediction.
Article Details
This work is licensed under a Creative Commons Attribution 4.0 International License.
References
Adler, A. I., & Painsky, A. (2022). Feature importance in gradient boosting trees with cross-validation feature selection. Entropy, 24(5), 687. https://doi.org/10.3390/e24050687
Al-Selwi, S. M., Hassan, M. F., Abdulkadir, S. J., Muneer, A., Sumiea, E. H., Alqushaibi, A., & Ragab, M. G. (2024). RNN-LSTM: From applications to modeling techniques and beyond-systematic review. Journal of King Saud University-Computer and Information Sciences, 36(5), 102068. https://doi.org/10.1016/j.jksuci.2024.102068
Alsharekh, M. F., Habib, S., Dewi, D. A., Albattah, W., Islam, M., & Albahli, S. (2022). Improving the efficiency of multistep short-term electricity load forecasting via R-CNN with ML-LSTM. Sensors, 22(18), 6913. https://doi.org/10.3390/s22186913
Bram, A. K., Ofori, C., Mangudhla, T., & Nuta, A. C. (2025). Exploring currency interdependence in West Africa: A time-varying parameter vector autoregression analysis. The Journal of Risk Finance, 26(2), 320–344. https://doi.org/10.1108/JRF-10-2024-0310
Buratto, W. G., Muniz, R. N., Nied, A., Barros, C. F. D. O., Cardoso, R., & Gonzalez, G. V. (2024). Wavelet CNN‐LSTM time series forecasting of electricity power generation considering biomass thermal systems. IET Generation, Transmission & Distribution, 18(21), 3437–3451. https://doi.org/10.1049/gtd2.13292
Chang, K., Chen, R., & Chevallier, J. (2018). Market fragmentation, liquidity measures and improvement perspectives from China’s emissions trading scheme pilots. Energy Economics, 75, 249–260. https://doi.org/10.1016/j.eneco.2018.07.010
Chen, T., Ye, J., Zhou, Y., Yu, Q., Wang, S., & Li, G. (2025). Prediction of carbon emission rights trading prices based on the CNN-LSTM Model in the context of carbon peak: Taking Guangdong Province as an example. Concurrency
and Computation: Practice and Experience, 37(12–14), e70121. https://doi.org/10.1002/cpe.70121
Dhanka, S., Sharma, A., Kumar, A. Maini, S., & Vundavilli, H. (2025). Advancements in hybrid machine learning models for biomedical disease classification using integration of hyperparameter-tuning and feature selection methodologies: A comprehensive review. Archives of Computational Methods in Engineering, 33, 289–324. https://doi.org/10.1007/s11831-025-10309-5
Dong, X., & Zhang, J. F. (2024). Heterogeneity of regional carbon emission markets in China: Evidence from multidimensional determinants. Energy Economics, 138, 107835. https://doi.org/10.1016/j.eneco.2024.107835
El Hokayem, J., Jamali, I., & Hejase, A. (2024). A forecasting model for oil prices using a large set of economic indicators. Journal of Forecasting, 43(5), 1615–1624. https://doi.org/10.1002/for.3087
Escribano, A., Koczar, M. W., Jareño, F., & Esparcia, C. (2023). Shock transmission between crude oil prices and stock markets. Resources Policy, 83, 103754. https://doi.org/10.1016/j.resourpol.2023.103754
Ghimire, S., Deo, R. C., Raj, N., & Mi, J. (2019). Deep solar radiation forecasting with convolutional neural network and long short-term memory network algorithms. Applied Energy, 253, 113541. https://doi.org/10.1016/j.apenergy.2019.113541
Goh, C. W., Chai, J., Rahman, A., & Ong, W. E. (2024). Crude palm oil price prediction using simulated annealing-based support vector regression (SASVR). Asian Academy of Management Journal of Accounting and Finance, 20(1), 305–333. https://doi.org/10.21315/aamjaf2024.20.1.10
Huang, Z., & Zhang, W. (2024). Forecasting carbon prices in China’s pilot carbon market: A multi-source information approach with conditional generative adversarial networks. Journal of Environmental Management, 359, 120967. https://doi.org/10.1016/j.jenvman.2024.120967
He, J., Ng, K. H., Shelton, P., & David, A. (2026). Modelling volatility and return based on a two-stage Log-BiACARR framework and intraday information: Evidence from Guangdong and Hubei carbon emissions trading markets. Physica A: Statistical Mechanics and its Applications, 681, 131097. https://doi.org/10.1016/j.physa.2025.131097
Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9(8), 1735–1780. https://doi.org/10.1162/neco.1997.9.8.1735
Jia, S., Tan, Z., & Li, C. (2025). Carbon prices forecasting based on sliding time window and improved support vector regression. Computing, 107(2), 53. https://doi.org/10.1007/s00607-024-01404-9
Jin, Y., Acquah, M. A., Seo, M., & Han, S. (2022). Short-term electric load prediction using transfer learning with interval estimate adjustment. Energy and Buildings, 258, 111846. https://doi.org/10.1016/j.enbuild.2022.111846
Jung, Y. (2018). Multiple predicting K-fold cross-validation for model selection. Journal of Nonparametric Statistics, 30(1), 197–215. https://doi.org/10.1080/10485252.2017.1404598
Krokida, S. I., Lambertides, N., Savva, C. S., & Tsouknidis, D. A. (2020). The effects of oil price shocks on the prices of EU emission trading system and European stock returns. The European Journal of Finance, 26(1), 1–13. https://doi.org/10.1080/1351847X.2019.1637358
Li, H., & Lei, M. (2018). The influencing factors of China carbon price: A study based on carbon trading market in Hubei province. IOP Conference Series: Earth and Environmental Science, 121(5), 052073. https://doi.org/10.1088/1755-1315/121/5/052073
Li, J., Yao, Y., & Wang, X. (2022). The first compliance cycle of China’s national emissions trading scheme: Insights and implications. Carbon Neutrality, 1(1), 34. https://doi.org/10.1007/s43979-022-00035-3
Lin, B., & Jia, Z. (2019). Impacts of carbon price level in carbon emission trading market. Applied Energy, 239, 157–170. https://doi.org/10.1016/j.apenergy.2019.01.194
Ling, M., & Cao, G. (2024). Carbon trading price forecasting based on parameter optimization VMD and deep network CNN-LSTM model. International Journal of Financial Engineering, 11(1), 2450002. https://doi.org/10.1142/S2424786324500026
Liu, X., Zhou, X., Zhu, B., & Wang, P. (2020). Measuring the efficiency of China’s carbon market: A comparison between efficient and fractal market hypotheses. Journal of Cleaner Production, 271, 122885. https://doi.org/10.1016/j.jclepro.2020.122885
Liu, X., & Jin, Z. (2020). An analysis of the interactions between electricity, fossil fuel and carbon market prices in Guangdong, China. Energy for Sustainable Development, 55, 82–94. https://doi.org/10.1016/j.esd.2020.01.008
Lu, X., Yan, H., He, P., & Apergis, N. (2025). Multifractal relationship between decomposed oil price shocks and trading volume. Humanities and Social Sciences Communications, 12(1), 1–16. https://doi.org/10.1057/s41599-025-05227-7
Luo, E., Shi, L., Liu, J., Wu, Z., Duan, G., Zeng, L., & Huang, T. (2024). MNPM: Research on metabolic neural network prediction model for predicting carbon emission accuracy. Environmental Research Communications, 6(11), 115034. https://doi.org/10.1088/2515-7620/ad9086
Montesinos López, O. A., Montesinos López, A., & Crossa, J. (2022). Convolutional neural networks. In Multivariate statistical machine learning methods for genomic prediction (pp. 533–577). Cham: Springer International Publishing. https://doi.org/10.1007/978-3-030-89010-0_13
Otto, P., & Schmid, W. (2023). A general framework for spatial GARCH models. Statistical Papers, 64(5), 1721–1747. https://doi.org/10.1007/s00362-022-01357-1
Perifanis, T., & Dagoumas, A. (2021). Crude oil price determinants and multi-sectoral effects: A review. Energy Sources, Part B: Economics, Planning, and Policy, 16(9), 787–860. https://doi.org/10.1080/15567249.2021.1922956
Rashid, M., Kamruzzaman, J., Imam, T., Wibowo, S., & Gordon, S. (2022). A tree-based stacking ensemble technique with feature selection for network intrusion detection. Applied Intelligence, 52(9), 9768–9781. https://doi.org/10.1007/s10489-021-02968-1
Sahin, E. K. (2020). Assessing the predictive capability of ensemble tree methods for landslide susceptibility mapping using XGBoost, gradient boosting machine, and random forest. SN Applied Sciences, 2(7), 1308. https://doi.org/10.1007/s42452-020-3060-1
Shah, J., Vaidya, D., & Shah, M. (2022). A comprehensive review on multiple hybrid deep learning approaches for stock prediction. Intelligent Systems with Applications, 16, 200111. https://doi.org/10.1016/j.iswa.2022.200111
Shih, S. Y., Sun, F. K., & Lee, H. Y. (2019). Temporal pattern attention for multivariate time series forecasting. Machine Learning, 108, 1421–1441. https://doi.org/10.1007/s10994-019-05815-0
Shin, Y., Kim, M., Cai, C., & Chang, Q. (2019). FARVaR: Functional Autoregressive Value-at-Risk. Journal of Financial Econometrics, 17, 284–337. https://doi.org/10.1093/jjfinec/nby031
Song, X., Zhang, W., Ge, Z., Huang, S., Huang, Y., & Xiong, S. (2022). A study of the influencing factors on the carbon emission trading price in China based on the improved gray relational analysis model. Sustainability, 14(13), 8002. https://doi.org/10.3390/su14138002
Srinivasan, S., Kumarasamy, S., Andreadakis, Z. E., & Lind, P. G. (2023). Artificial intelligence and mathematical models of power grids driven by renewable energy sources: A survey. Energies, 16(14), 5383. https://doi.org/10.3390/en16145383
Tan, K., Wu, Y., Xu, F., Ji, X., & Li, C. (2024). Modeling and analyzing carbon emission market volatility and impact: Evidence from Guangdong province, China. Systems, 12(11), 458. https://doi.org/10.3390/systems12110458
Tange, R. I., Rasmussen, M. A., Taira, E., & Bro, R. (2017). Benchmarking support vector regression against partial least squares regression and artificial neural network: Effect of sample size on model performance. Journal of Near Infrared Spectroscopy, 25(6), 381–390. https://doi.org/10.1177/0967033517734945
Tsai, I. C. (2024). Fossil energy risk exposure of the UK electricity system: The moderating role of electricity generation mixes and energy source. Energy Policy, 188, 114065. https://doi.org/10.1016/j.enpol.2024.114065
Villoria-Sáez, P., Tam, V. W., del Río Merino, M., Arrebola, C. V., & Wang, X. (2016). Effectiveness of greenhouse-gas emission trading schemes implementation: A review on legislations. Journal of Cleaner Production, 127, 49–58. https://doi.org/10.1016/j.jclepro.2016.03.148
Wang, W., Yang, Y., Wang, X., Wang, W., & Li, J. (2019). Development of convolutional neural network and its application in image classification: A survey. Optical Engineering, 58(4), 040901–040901. https://doi.org/10.1117/1.OE.58.4.040901
Wang, W., Zhao, X., Zhang, Q., Fu, C., & Xie, P. (2022). Auction mechanism design of the Chinese national carbon market for carbon neutralization. Chinese Journal of Population, Resources and Environment, 20(2), 115–124. https://doi.org/10.1016/j.cjpre.2022.06.002
Wang, Z., Xing, T., & Wang, X. (2025). Economic uncertainty and stock market asymmetric volatility: Analysis based on the asymmetric GARCH-MIDAS model. International Journal of Emerging Markets, 20(8), 3488–3511. https://doi.org/10.1108/IJOEM-05-2023-0841
Zhang, W., & Wu, Z. (2022). Optimal hybrid framework for carbon price forecasting using time series analysis and least squares support vector machine. Journal of Forecasting, 41(3), 615–632. https://doi.org/10.1002/for.2831
Zhao, Y., Liu, L., Wang, A., & Liu, M. (2023). A novel deep learning based forecasting model for carbon emissions trading: A comparative analysis of regional markets. Solar Energy, 262, 111863. https://doi.org/10.1016/j.solener.2023.111863
Zhou, F., Huang, Z., & Zhang, C. (2022). Carbon price forecasting based on CEEMDAN and LSTM. Applied Energy, 311, 118601. https://doi.org/10.1016/j.apenergy.2022.118601
Zhou, K., & Li, Y. (2019). Influencing factors and fluctuation characteristics of China’s carbon emission trading price. Physica A: Statistical Mechanics and its Applications, 524, 459–474. https://doi.org/10.1016/j.physa.2019.04.249