A Study on Price Volatility in the Carbon Emissions Trading Market Based on the GARCH-ANN Model
DOI:
https://doi.org/10.61173/z26a0q47Keywords:
Emissions Trading, Price Volatility, GARCH Model, Artificial Neural Network (ANN), Policy Shock, Risk ManagementAbstract
With the advancement of the global "dual-carbon" strategy, emissions trading systems (ETS) have gradually become a central policy tool in driving green economic transformation. However, sharp fluctuations in carbon prices not only threaten market stability but also directly impact corporate emission reduction decisions and long-term investments. This study innovatively combines the GARCH model's ability to capture volatility clustering with the artificial neural network (ANN)'s strong capability in modeling nonlinear relationships to construct a GARCH-ANN hybrid model. The model systematically analyzes the volatility characteristics of carbon allowance prices and their dynamic response mechanisms to exogenous shocks. Taking the EU Emissions Trading System (EU ETS) and China’s pilot markets as research objects, the study incorporates high-frequency trading data and policy dummy variables, and empirically tests the predictive performance of the hybrid model. The results show that the hybrid model significantly outperforms single models, and policy shocks exhibit time-varying effects. This study provides both theoretical and empirical support for the design of carbon market regulatory policies, corporate green investment decisions, and the interconnection of international carbon markets.
References
[1] Lü, Y. B., & Shao, L. B. (2015). A Study on the Price Volatility of China’s Carbon Emissions Trading — Based on GARCH Family Models. *Price Theory and Practice*, (12), 62–64.
[2] Jiang, T. (2023). Research on the Price Volatility Characteristics of Carbon Emissions Trading Based on ARMA- GARCH and VAR Models. *Statistics and Applications*, 12(1), 173–185.
[3] Li, G. X. (2022). Measurement of Price Volatility Risk in China’s Carbon Market Based on the T-GARCH-VAR Model. [Master’s thesis, University of International Business and Economics].
[4] Zhang, Z. H. (2020). Research on Volatility Forecasting Model of China’s Gold Prices Based on Deep Learning. [Master’s thesis, Southwestern University of Finance and Economics].
[5] Liu, H. Q., Zhao, M. M., Zhang, J., et al. (2022). The Impact of Carbon Trading Policies on Carbon Productivity. *Science and Economy*, 35(6), 6–10.
[6] Xia, R. T. (2018). Research on the Price Volatility of China’s Carbon Emissions Trading — Based on AR-GARCH Model Analysis. *China Price*, (5), 52–54.
[7] Lin, Q. Q., & Xia, R. T. (2018). China’s Carbon Market Operation, Problems, and Countermeasures. *Modern Management Science*, (8), 3–5.
[8] Liu, N. (2022). Research on Carbon Price Forecasting Based on LSTM/GARCH-SVR Model. [Master’s thesis, Chongqing University].
[9] Gan, T. Q., Li, S. B., & Zhou, Z. Y. (2024). The Carbon Reduction Effect of Green Bonds — From the Perspective of Investors’ Green Preferences. *China Population, Resources and Environment*, 34(11), 52–64.
[10] Yan, X. Y. (2024). Analysis of CITIC Securities Stock Return Using ARMA-GARCH and VAR Models. *Business Exhibition Economy*, (11), 98–101.
[11] Wen, L. (2021). Volatility Forecasting of Copper Spot Prices Based on GARCH and Neural Network Hybrid Model. [Master’s thesis, Southwestern University of Finance and Economics].
[12] Fu, S. Y., & Guo, D. P. (2020). Application of Artificial Neural Networks in Microloan Credit Risk Control — A Case Study of Bank A. *Fujian Finance*, (11), 50–57.
[13] Cheng, T. X. (2023). A CEV Option Pricing Model Based on Neural Networks and the GARCH Model. [Master’s thesis, Southwestern University of Finance and Economics].
Downloads
Published
Issue
Section
License
Copyright (c) 2025 by the authors.
This work is licensed under a Creative Commons Attribution 4.0 International License.
