A sentiment-driven three-stage approach for multi-scale carbon price prediction

Abstract An accurate calculation method of carbon trading price is of great significance to strengthening energy saving and emission reduction. Due to the nonlinear and non-stationary characteristics of the carbon price, it is difficult to predict the carbon price accurately. This paper proposes a n...

Full description

Saved in:
Bibliographic Details
Main Authors: Yongliang Liu, Chunling Tang, Aiying Zhou, Kai Yang, Huaiyu Yuan
Format: Article
Language:English
Published: Springer 2025-06-01
Series:Discover Sustainability
Subjects:
Online Access:https://doi.org/10.1007/s43621-025-01258-x
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849433145212928000
author Yongliang Liu
Chunling Tang
Aiying Zhou
Kai Yang
Huaiyu Yuan
author_facet Yongliang Liu
Chunling Tang
Aiying Zhou
Kai Yang
Huaiyu Yuan
author_sort Yongliang Liu
collection DOAJ
description Abstract An accurate calculation method of carbon trading price is of great significance to strengthening energy saving and emission reduction. Due to the nonlinear and non-stationary characteristics of the carbon price, it is difficult to predict the carbon price accurately. This paper proposes a new hybrid model for carbon trading price forecasting. The model fuses complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) with extreme gradient boosting (XGBoost) and long short-term memory (LSTM) networks, and leverages SnowNLP to derive sentiment scores from news text and the Baidu Index. To demonstrate the superiority of the proposed model, 5 chinese carbon emissions trading markets are selected for the predictions. The model shows better performance across all markets, improving by 4.20% to 17.89% over the CEEMDAN-LSTM model and outperforming other benchmarks. Furthermore, ablation experiments and parametric sensitivity analyses were carried out to verify the contribution of each component and the overall model’ s robustness. It offers a reliable and stable forecasting tool for stakeholders in the carbon market.
format Article
id doaj-art-1be5cf71abeb4fc681f7fcca6b9864c6
institution Kabale University
issn 2662-9984
language English
publishDate 2025-06-01
publisher Springer
record_format Article
series Discover Sustainability
spelling doaj-art-1be5cf71abeb4fc681f7fcca6b9864c62025-08-20T03:27:10ZengSpringerDiscover Sustainability2662-99842025-06-016113210.1007/s43621-025-01258-xA sentiment-driven three-stage approach for multi-scale carbon price predictionYongliang Liu0Chunling Tang1Aiying Zhou2Kai Yang3Huaiyu Yuan4School of Economics, Central South University of Forestry and TechnologySchool of Economics, Central South University of Forestry and TechnologySchool of Economics, Central South University of Forestry and TechnologyShenzhen International Graduate School, Tsinghua UniversitySchool of Economics, Central South University of Forestry and TechnologyAbstract An accurate calculation method of carbon trading price is of great significance to strengthening energy saving and emission reduction. Due to the nonlinear and non-stationary characteristics of the carbon price, it is difficult to predict the carbon price accurately. This paper proposes a new hybrid model for carbon trading price forecasting. The model fuses complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) with extreme gradient boosting (XGBoost) and long short-term memory (LSTM) networks, and leverages SnowNLP to derive sentiment scores from news text and the Baidu Index. To demonstrate the superiority of the proposed model, 5 chinese carbon emissions trading markets are selected for the predictions. The model shows better performance across all markets, improving by 4.20% to 17.89% over the CEEMDAN-LSTM model and outperforming other benchmarks. Furthermore, ablation experiments and parametric sensitivity analyses were carried out to verify the contribution of each component and the overall model’ s robustness. It offers a reliable and stable forecasting tool for stakeholders in the carbon market.https://doi.org/10.1007/s43621-025-01258-xCarbon trading price forecastingSentiment analysisCEEMDANXGBoostLong short-term memoryDeep learning
spellingShingle Yongliang Liu
Chunling Tang
Aiying Zhou
Kai Yang
Huaiyu Yuan
A sentiment-driven three-stage approach for multi-scale carbon price prediction
Discover Sustainability
Carbon trading price forecasting
Sentiment analysis
CEEMDAN
XGBoost
Long short-term memory
Deep learning
title A sentiment-driven three-stage approach for multi-scale carbon price prediction
title_full A sentiment-driven three-stage approach for multi-scale carbon price prediction
title_fullStr A sentiment-driven three-stage approach for multi-scale carbon price prediction
title_full_unstemmed A sentiment-driven three-stage approach for multi-scale carbon price prediction
title_short A sentiment-driven three-stage approach for multi-scale carbon price prediction
title_sort sentiment driven three stage approach for multi scale carbon price prediction
topic Carbon trading price forecasting
Sentiment analysis
CEEMDAN
XGBoost
Long short-term memory
Deep learning
url https://doi.org/10.1007/s43621-025-01258-x
work_keys_str_mv AT yongliangliu asentimentdriventhreestageapproachformultiscalecarbonpriceprediction
AT chunlingtang asentimentdriventhreestageapproachformultiscalecarbonpriceprediction
AT aiyingzhou asentimentdriventhreestageapproachformultiscalecarbonpriceprediction
AT kaiyang asentimentdriventhreestageapproachformultiscalecarbonpriceprediction
AT huaiyuyuan asentimentdriventhreestageapproachformultiscalecarbonpriceprediction
AT yongliangliu sentimentdriventhreestageapproachformultiscalecarbonpriceprediction
AT chunlingtang sentimentdriventhreestageapproachformultiscalecarbonpriceprediction
AT aiyingzhou sentimentdriventhreestageapproachformultiscalecarbonpriceprediction
AT kaiyang sentimentdriventhreestageapproachformultiscalecarbonpriceprediction
AT huaiyuyuan sentimentdriventhreestageapproachformultiscalecarbonpriceprediction