Scholarlink

Carbon trading price plays an important role in curbing global warming, helping the healthy development of carbon market, and providing reference for the formulation of relevant policies and enterprises' participation. Based on the Long Short-Term Memory network (LSTM) model, this paper predicts the market trend of the closing price of Guangdong Provincial Carbon Emission Allowances (GDEA). In the study, a comprehensive consideration of macroeconomic, energy costs, exchange rate fluctuations and international carbon trading prices and other dimensions, 13 structural influencing factors, and 36 Internet search index influencing factors were selected. Using the LASSO algorithm, we identified 11 key influencers from these factors, six from structured data and five from web search indices. Using these key factors as inputs, the LSTM model parameters are optimized by particle swarm optimization (PSO) technology, and then the price component of GDEA is predicted, and the overall prediction results are obtained by synthesizing the three component predicted values. The results show that the linear model has the best performance in forecasting accuracy and can predict the trend of carbon trading price more accurately. This study provides valuable decision support for the participants of the international carbon trading market, helps to promote the steady development of the carbon market, and provides a strategic basis for coping with global warming.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Prediction of Foreign Carbon Emission Rights Market Price Trend Using Long- and Short-Term Memory Network

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Bingbing Song,
  • Pan Wu,
  • Kangping Qing,
  • Xiaobi Teng,
  • Hongyu He,
  • Wenhai Huang

摘要

Carbon trading price plays an important role in curbing global warming, helping the healthy development of carbon market, and providing reference for the formulation of relevant policies and enterprises' participation. Based on the Long Short-Term Memory network (LSTM) model, this paper predicts the market trend of the closing price of Guangdong Provincial Carbon Emission Allowances (GDEA). In the study, a comprehensive consideration of macroeconomic, energy costs, exchange rate fluctuations and international carbon trading prices and other dimensions, 13 structural influencing factors, and 36 Internet search index influencing factors were selected. Using the LASSO algorithm, we identified 11 key influencers from these factors, six from structured data and five from web search indices. Using these key factors as inputs, the LSTM model parameters are optimized by particle swarm optimization (PSO) technology, and then the price component of GDEA is predicted, and the overall prediction results are obtained by synthesizing the three component predicted values. The results show that the linear model has the best performance in forecasting accuracy and can predict the trend of carbon trading price more accurately. This study provides valuable decision support for the participants of the international carbon trading market, helps to promote the steady development of the carbon market, and provides a strategic basis for coping with global warming.