Search

Predicting carbon prices is crucial for the growth of China's carbon trading industry. This paper proposes a residual correction model that considers multiple influencing factors. First, the best historical data and main external factors input by the model are determined by using the partial autocorrelation function and Spearman correlation analysis, and the carbon price forecasting index system is constructed. Second, the whale optimization algorithm (WOA) is utilized to determine the optimal parameters of the extreme gradient boosting (XGBoost), and the WOA‐XGBoost model is built to perform preliminary carbon price forecasts and obtain the residual series. Finally, the carbon price residual series undergoes decomposition into multiple components utilizing the complete ensemble empirical mode decomposition for subsequent forecasting and the aggregation of outcomes. Experiments are conducted to predict two carbon trading markets in Hubei and Guangzhou, and a feature importance analysis is performed. The results indicate that the proposed hybrid model consistently outperforms the comparative models in terms of prediction accuracy. Furthermore, it is revealed that historical carbon prices and European Union carbon prices are the key factors influencing the prediction of carbon market prices. [ABSTRACT FROM AUTHOR]

As the financialization of carbon emission right, developing effective carbon asset trading strategy is important for both investors and regulators. Traditional trading strategy based on technical analysis is hardly profitable due to high complexity inherent in carbon markets. In order to increase investment returns and reduce risk in carbon market, this paper introduces PSO-VMD-DRL, an innovative carbon asset trading strategy that integrates signal decomposition technology and deep reinforcement learning (DRL). Firstly, the carbon price is decomposed into multiple components by variational mode decomposition (VMD) optimized through particle swarm optimization (PSO) to extract frequency features and reduce noise. Then state representation of the environment (state space) is constructed based on the components and transaction data. Finally, deep reinforcement learning (PPO, A2C, DDPG) are performed separately based on state space to learn optimal trading strategy. Empirical studies based on the data from carbon markets of Hubei and Guangzhou validate that PSO-VMD-DRL can adapt to carbon asset with the better profitability and risk resistance. The PSO-VMD-DRL outperform the other comparison strategies with superiority in all evaluation indices, achieving annual return of 21.39%, 17.67%, 25.50% and 46.34%, 44.55%, 43.03% in carbon market of Hubei and Guangzhou. [ABSTRACT FROM AUTHOR]