文本数据驱动的碳交易价格区间二层分解预测方法  

A Two-layer Decomposition Method with Textual Data for Carbon Price Interval Forecast

作　　者：刘金培[1] 张了丹 陈意 陈华友[3] Liu Jinpei;Zhang Liaodan;Chen Yi;Chen Huayou(School of Business,Anhui University,Hefei 230601;School of Management,Zhejiang University,Hangzhou 310058;School of Mathematical Sciences,Anhui University,Hefei 230601)

机构地区：[1]安徽大学商学院,合肥230601 [2]浙江大学管理学院,杭州310058 [3]安徽大学数学科学学院,合肥230601

出　　处：《管理评论》2023年第12期31-39,共9页Management Review

基　　金：国家自然科学基金项目(72071001);教育部人文社会科学研究规划基金项目(20YJAZH066);安徽省自然科学基金项目(2008085MG226,2108085QG288);安徽省高校优秀青年人才支持计划项目(gxyqZD2022001);安徽省哲学社会科学规划青年项目(AHSKQ2020D08)。

摘　　要：新闻文本数据所包含的情感信息影响着管理者与投资者的决策过程,因而可为碳价预测提供额外信息。本文提出了一种文本数据驱动的碳价区间二层分解预测模型,首先爬取碳排放网上相关新闻文本并计算其情感得分,接着对碳价区间与情感数据进行EMD-WTS二层分解,并基于SE算法将分解结果重构为对应时序的高、低频及趋势项,最后运用LSTM网络对所得序列开展预测,叠加集成后得到最终预测结果。实证实验及对比实验发现,上述模型在有效利用多源信息的同时充分挖掘了碳价区间复杂波动时序中的细节特征,预测效果更为显著。The emotional information contained in news textual data affects the decision-making process of managers and investors.Hence,it can be used to improve the forecasting accuracy of carbon price interval.In this paper,a two-layer decomposition model driven by textual data is proposed.Relevant news texts associated with the carbon emission in network are climbed,of which the sentiment scores are calculated,at first.Secondly,the carbon price interval and sentiment data are decomposed in EMD-WTS decomposition meth-od,and the results are reconstructed into high,low frequency and trend items corresponding to time series based on SE algorithm.Even-tually,the LSTM network is used to predict the obtained sequences,and the final prediction result is gained after superposition and inte-gration.The empirical and comparative experiments show that the proposed model can not only effectively utilize the multi-source infor-mation,but also fully mine the detailed features in the time series of complex fluctuation of carbon price range,thus achieving a more significant prediction effect.

关 键 词：碳价格预测 文本数据 二层分解 区间预测 LSTM 

分 类 号：F832.5[经济管理—金融学] X196[环境科学与工程—环境科学]