基于文本信息的碳价预测
Carbon Price Prediction Based on Text Information
DOI: 10.12677/ecl.2024.1341615, PDF,   
作者: 孙梦敏：贵州大学经济学院，贵州 贵阳
关键词: 深度学习；文本信息；碳价预测；Deep Learning； Text Information； Carbon Price Prediction
摘要: 为探究文本信息对我国碳价预测的影响，本研究搜集了2014年1月1日至2021年12月31日期间与碳价相关的新闻及政策资料，并通过相似度分析将文本信息进行量化处理。随后，本研究将量化后的文本信息与期货结算价、WTI原油价格、欧元兑人民币汇率、期货成交量以及核证减排量、空气质量指数等指标相结合，以验证文本信息在预测国内碳价方面的有效性。经过分析，得出以下结论：1) ARIMA模型和LSTM模型在捕捉序列信息方面表现更为出色，其效果超越了其他模型。2) 文本中蕴含了对碳价预测有帮助的有效信息，这些信息能够提高模型的预测准确性。总的来说，对碳价进行更精确的预测，能帮助企业及时掌握市场动态，提前制定投资决策；同时也有利于政府适时实施宏观调控。
Abstract: In order to explore the impact of text information on China’s carbon price forecast, this study collected news and policy data related to carbon price from January 1, 2014 to December 31, 2021, and quantitatively processed the text information through similarity analysis. Subsequently, this study combined the quantified text information with futures settlement price, WTI crude oil price, euro-RMB exchange rate, futures trading volume, certified emission reduction, air quality index and other indicators to verify the validity of text information in predicting domestic carbon price. After analysis, the following conclusions are drawn: 1) ARIMA model and LSTM model perform better in capturing sequence information than other models. 2) The text contains effective information helpful for carbon price prediction, which can improve the prediction accuracy of the model. In general, a more accurate forecast of carbon prices can help enterprises grasp market dynamics in time and make investment decisions in advance. At the same time, it will also help the government carry out macro-control in a timely manner.
文章引用：孙梦敏. 基于文本信息的碳价预测[J]. 电子商务评论, 2024, 13(4): 4056-4066. https://doi.org/10.12677/ecl.2024.1341615

参考文献

[1] Daskalakis, G. and Markellos, R.N. (2009) Are Electricity Risk Premia Affected by Emission Allowance Prices? Evidence from the EEX, Nord Pool and Powernext. Energy Policy, 37, 2594-2604. [Google Scholar] [CrossRef] 
[2] 谢治菊, 彭智邦. 嵌入式有为与适应性有效: 东西部消费协作中的政府与市场[J]. 中州学刊, 2022(11): 9-19.
[3] 魏宇, 张佳豪, 陈晓丹. 基于DMS和DMA的我国碳排放权交易价格预测方法——来自湖北碳市场的经验证据[J]. 系统工程, 2022, 40(4): 1-16.
[4] 王娜. 基于大数据的碳价预测[J]. 统计研究, 2016, 33(11): 56-62.
[5] Mansanet-Bataller, M., Pardo, A. and Valor, E. (2007) CO2 Prices, Energy and Weather. The Energy Journal, 28, 73-92. [Google Scholar] [CrossRef] 
[6] Mansanet-Bataller, M. and Pardo, A. (2009) Impacts of Regulatory Announcements on CO2 Prices. The Journal of Energy Markets, 2, 75-107. [Google Scholar] [CrossRef] 
[7] 朱帮助, 王平, 魏一鸣. 基于EMD的碳市场价格影响因素多尺度分析[J]. 经济学动态, 2012(6): 92-97.
[8] Lovcha, Y., Perez-Laborda, A. and Sikora, I. (2022) The Determinants of CO2 Prices in the EU Emission Trading System. Applied Energy, 305, Article 117903. [Google Scholar] [CrossRef] 
[9] 王丹舟, 杨德天. 中国碳排放权交易价格的驱动因素[J]. 首都经济贸易大学学报, 2018, 20(5): 87-95.
[10] 张云. 中国碳交易价格驱动因素研究——基于市场基本面与政策信息的双重视角[J]. 社会科学辑刊, 2018(1): 111-120.
[11] 吕靖烨, 杨华, 郭泽. 基于GA-RS的中国碳排放权价格影响因素的分解研究[J]. 生态经济, 2019, 35(11): 42-47+130.
[12] 张晨, 胡贝贝. 基于误差校正的多因素BP国际碳市场价格预测[J]. 价格月刊, 2017(1): 11-18.
[13] Sun, W. and Zhang, J. (2020) Carbon Price Prediction Based on Ensemble Empirical Mode Decomposition and Extreme Learning Machine Optimized by Improved Bat Algorithm Considering Energy Price Factors. Energies, 13, Article 3471. [Google Scholar] [CrossRef] 
[14] Yang, S., Chen, D., Li, S. and Wang, W. (2020) Carbon Price Forecasting Based on Modified Ensemble Empirical Mode Decomposition and Long Short-Term Memory Optimized by Improved Whale Optimization Algorithm. Science of the Total Environment, 716, Article 137117. [Google Scholar] [CrossRef] [PubMed]
[15] Zhou, J. and Chen, D. (2021) Carbon Price Forecasting Based on Improved CEEMDAN and Extreme Learning Machine Optimized by Sparrow Search Algorithm. Sustainability, 13, Article 4896. [Google Scholar] [CrossRef] 
[16] Chen, P., Vivian, A. and Ye, C. (2021) Forecasting Carbon Futures Price: A Hybrid Method Incorporating Fuzzy Entropy and Extreme Learning Machine. Annals of Operations Research, 313, 559-601. [Google Scholar] [CrossRef] [PubMed]
[17] Jiang, L. and Wu, P. (2015) International Carbon Market Price Forecasting Using an Integration Model Based on SVR. Proceedings of the 2015 International conference on Engineering Management, Engineering Education and Information Technology, Chengdu, 6-9 December 2015, 303-308. [Google Scholar] [CrossRef] 
[18] 蒋锋, 彭紫君. 基于混沌PSO优化BP神经网络的碳价预测[J]. 统计与信息论坛, 2018, 33(5): 93-98.
[19] Xu, H., Wang, M., Jiang, S. and Yang, W. (2020) Carbon Price Forecasting with Complex Network and Extreme Learning Machine. Physica A: Statistical Mechanics and Its Applications, 545, Article 122830.
[20] Wang, J., Cui, Q. and Sun, X. (2021) A Novel Framework for Carbon Price Prediction Using Comprehensive Feature Screening, Bidirectional Gate Recurrent Unit and Gaussian Process Regression. Journal of Cleaner Production, 314, Article 128024.

为你推荐