<abstract xmlns="http://www.w3.org/1999/xhtml">

<p>With the continuous development of industrialized society, carbon emissions have become a significant global challenge. Carbon trading, as a crucial measure to mitigate carbon emissions, has garnered substantial attention in the context of market prediction analysis. Addressing the nonlinear and nonstationary nature of carbon trading prices, this study proposes a novel prediction model based on signal decomposition and deep learning. A GUR neural network model, integrated with an attention mechanism, is constructed within a deep learning framework. The model utilizes Ensemble Empirical Mode Decomposition (EEMD) to address the issue of non-smooth and nonlinear panel data, further enhanced by the Symbiotic Organism Search (SOA) algorithm. This approach culminates in an advanced price prediction model for China’s carbon trading market. Analysis of relevant data from 2014 to 2022 reveals several fluctuations in carbon trading prices, with transaction prices peaking at 68 yuan. The proposed method demonstrates superior performance metrics, with RMSE, MAE, and MAPE values of 0.512, 0.395, and 1.108%, respectively, outperforming other methods. This study offers an effective approach for predicting carbon trading market prices, providing valuable insights for optimizing and managing carbon market trading and development.</p>
</abstract>

With the continuous development of industrialized society, carbon emissions have become a significant global challenge. Carbon trading, as a crucial measure to mitigate carbon emissions, has garnered substantial attention in the context of market prediction analysis. Addressing the nonlinear and nonstationary nature of carbon trading prices, this study proposes a novel prediction model based on signal decomposition and deep learning. A GUR neural network model, integrated with an attention mechanism, is constructed within a deep learning framework. The model utilizes Ensemble Empirical Mode Decomposition (EEMD) to address the issue of non-smooth and nonlinear panel data, further enhanced by the Symbiotic Organism Search (SOA) algorithm. This approach culminates in an advanced price prediction model for China’s carbon trading market. Analysis of relevant data from 2014 to 2022 reveals several fluctuations in carbon trading prices, with transaction prices peaking at 68 yuan. The proposed method demonstrates superior performance metrics, with RMSE, MAE, and MAPE values of 0.512, 0.395, and 1.108%, respectively, outperforming other methods. This study offers an effective approach for predicting carbon trading market prices, providing valuable insights for optimizing and managing carbon market trading and development.

Analysis and research on China’s carbon trading market and transaction prices based on signal decomposition model and deep learning model

Applied Mathematics and Nonlinear Sciences

This work is licensed under the Creative Commons Attribution 4.0 International License.

With the continuous development of industrialized society, carbon emissions have become a significant global challenge. Carbon trading, as a crucial measure to...

Analysis and research on China’s carbon trading market and transaction prices based on signal decomposition model and deep learning model

Data publikacji: 05 sie 2024

Zakres stron: -

Otrzymano: 19 kwi 2024

Przyjęty: 05 lip 2024

DOI: https://doi.org/10.2478/amns-2024-1893

Słowa kluczowe
Deep learning, GUR neural network, EEMD decomposition, Price prediction, Carbon trading market

© 2024 Yilin Wang., published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Analysis and research on China’s carbon trading market and transaction prices based on signal decomposition model and deep learning model

Data publikacji: 05 sie 2024

Zakres stron: -

Otrzymano: 19 kwi 2024

Przyjęty: 05 lip 2024

DOI: https://doi.org/10.2478/amns-2024-1893

Słowa kluczoweDeep learning, GUR neural network, EEMD decomposition, Price prediction, Carbon trading market

© 2024 Yilin Wang., published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Słowa kluczowe
Deep learning, GUR neural network, EEMD decomposition, Price prediction, Carbon trading market