Leveraging machine learning to forecast carbon returns: Factors from energy markets.

Carbon market is the most effective market tool for carbon emission reduction. China, the largest carbon emitter in the world, established the national carbon market in 2021, covering over 2000 key units in the power sector. Therefore, the forecasting of carbon price has profound implications for environmental and energy policies. In this paper, two traditional econometric model and three kinds of machine learning (ML) algorithms are used to predict carbon returns in the Chinese carbon trading market based on carefully selected predictors. Among all forecasting models, the Random Forest (RF) has the best forecasting performance, followed by some GARCH models using various factors. Compared with the traditional benchmark of ARMA model, the BP neural network (BP) and the GA improved BP method (GA-BP) are less competitive in predicting carbon returns in China because of their large forecasting errors. According to the optimal model, social attention to the carbon market, the international crude oil returns and the overall performance of the stock market are the most important predictors. The findings are robust to the change in the sample set. Overall, the ML approach shows an advantage in forecasting carbon returns, but the selection of predictors is also important. • Machine learning and econometric models are used to forecast carbon returns in China. • The selection of predictors is based on economic analysis. • The Random Forest (RF) outperforms the other ML and econometric methods. • The energy market is extremely important for predicting carbon returns. • Social concerns and stock market performance improve forecasting accuracy. [ABSTRACT FROM AUTHOR]