计算机工程与应用2025，Vol.61Issue(10)：350-360,11.DOI:10.3778/j.issn.1002-8331.2401-0109
融合多源信息的碳价时滞组合预测
Carbon Price Forecasting Based on Multi-Source Information Fusion and Time-Delay Effect
摘要
Abstract
The carbon price is the core element of the carbon market,and its fluctuations are influenced by numerous factors and their time-delay effects.To precisely forecast the price of Chinese emission allowances(CEA)in the national carbon market,structured influencing factors are selected from five dimensions:related carbon markets,economic development,foreign energy,domestic energy,and the RMB exchange rate.Unstructured influencing factors are crawled from three dimensions:economic policy,environmental impact,and user preference,using the Baidu search engine.The MIV-BP model is introduced to screen the main influencing factors and carbon price,and the time-delay of multi-source factors are estimated based on maximum information coefficient(MIC).On this basis,a time-delay combined prediction model for carbon price is constructed based on MIC,LSTM and BP.Compared with baseline models such as LSTM,BP,LSTM-BP,and time-delay baseline models MIC-LSTM,MIC-BP,and MIC-LSTM-GBDT,the effectiveness of the new model is verified.The results indicate that the introduction of time-delay information is helpful to improve the prediction accuracy of the model.Compared with the baseline and time-delay baseline models,the MIC-LSTM-BP model has the highest pre-cision in forecasting CEA prices and the best capability to follow price volatility.关键词
全国碳市场/多源信息/影响因素筛选/时滞估计/组合预测/MIC-LSTM-BP模型Key words
national carbon market/multi-source information/influence factor screening/time-delay estimation/com-bined prediction/MIC-LSTM-BP model分类
经济学引用本文复制引用
邹艳,王淑平,李欣岷,龚科..融合多源信息的碳价时滞组合预测[J].计算机工程与应用,2025,61(10):350-360,11.基金项目
国家自然科学基金(71871034) （71871034）
教育部人文社科项目(23XJA630006) （23XJA630006）
重庆师范大学研究生科研创新项目(YKC24016). （YKC24016）
