湖北民族大学学报（自然科学版）2025，Vol.43Issue(2)：280-289,10.DOI:10.13501/j.cnki.42-1908/n.2025.06.012
基于VAR和ARIMA-LSTM模型的碳排放权交易价格影响因素分析及预测
Analysis and Prediction of Influencing Factors of Carbon Emission Trading Price Based on VAR and ARIMA-LSTM Model
摘要
Abstract
To analyze and predict the influencing factors of carbon emission trading prices,the Hubei carbon emission trading market was taken as the research object,and 11 influencing factors from five aspects(macroeconomics,energy prices,exchange rates,international carbon markets,and climate environment)were used for sorting and correlation analysis.At the same time,a vector autoregression(VAR)model was established for empirical analysis,and further,autoregressive integrated moving average(ARIMA)model,long short term memory(LSTM),and weighted combination models were further used for comparative prediction.The research found that:Carbon trading price fluctuations were mainly driven by their own historical prices,with a contribution rate of up to 98.07%;The prediction accuracy of the ARIMA-LSTM weighted combination model was significantly improved compared with the single model,with mean absolute percentage error(MAPE)reduced to 1.943 and root mean square error(RMSE)reduced to 0.915;The current carbon market in Hubei had problems such as an incomplete trading mechanism and a single price formation mechanism,which posed potential systemic risks.The research confirmed that it was urgent to improve the operational efficiency of the carbon market through measures such as improving market infrastructure construction and optimizing price formation mechanisms.The research results could provide methodological support for regulatory authorities to build a risk warning system and providing quantitative decision-making basis for climate policy formulation.关键词
碳排放权交易价格/影响因素/VAR模型/ARIMA模型/LSTM模型Key words
carbon emission trading price/influencing factors/VAR model/ARIMA model/LSTM model分类
管理科学引用本文复制引用
魏静,刘芙冉,袁婷,王婷..基于VAR和ARIMA-LSTM模型的碳排放权交易价格影响因素分析及预测[J].湖北民族大学学报（自然科学版）,2025,43(2):280-289,10.基金项目
成都信息工程大学引进人才科研启动项目(KYTZ202298). （KYTZ202298）
