Factor analysis and carbon price prediction based on empirical mode decomposition and least squares support vector machine optimized by improved particle swarm optimization

Abstract

With the development of China’s carbon market, there has been a growing interest in research on carbon prices. Using analysis and prediction, the mechanism of the carbon market could be improved and correct guidance from relevant policies might be provided. To improve the accuracy of prediction, a hybrid model based on factor analysis, empirical mode decomposition, improved particle swarm optimization, and the least squares support vector machine is proposed in this article to use when considering the historical carbon price and external factors affecting the carbon price. First, factor analysis is conducted to extract special factors as input variables. Then, the original carbon price sequences are decomposed by empirical mode decomposition. Ultimately, the least squares support vector machine optimized by improved particle swarm optimization is employed to calculate each sequence, and the final predicted result is integrated by the forecasting results of each sequence. Based on three typical carbon markets in China, the results show that the hybrid model is more accurate than comparable models when forecasting carbon prices combined with various factors.