Carbon transaction price prediction method and device based on news influence attenuation

• Main Authors: LIN RUIBIN, ZENG ZHIMEI, LI XIAOMING, YU ZEHUI, HUANG JUNJIE, ZHANG BOTING, ZHANG DABIN
• Format: Patent
• Language: Chinese; English
• Published: 15.08.2023
• Subjects: CALCULATING; COMPUTING; COUNTING; DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES; ELECTRIC DIGITAL DATA PROCESSING; PHYSICS; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR

The invention discloses a news influence attenuation-based carbon transaction price prediction method and apparatus. The method comprises the steps of collecting carbon transaction collection price data and carbon transaction news text data; performing data cleaning on the collected carbon transaction closing price data and the carbon transaction news text data; performing feature extraction on the cleaned news text data; visualizing data of the keywords by creating a word cloud; splicing the carbon transaction collection price features and the news text features under the same time scale; and performing prediction through a machine learning model, calculating error evaluation criteria of different models, and verifying the effectiveness of the proposed carbon transaction price prediction method based on news influence attenuation. According to the method, news factors influencing carbon transaction price fluctuation are considered, the carbon transaction price is predicted based on the text mining and machin