Prediction of Carbon Financial Transaction Price Based on CEEMD Denoising and PSO-LSSVM——Take Guangdong Province as an example

Climate change has an unprecedented impact on the world, and it is also important era proposition to be solved in China's development. Carbon emissions trading occupies position, which aims adapt global carbon neutrality context implement sustainable development requirements. The market mechanism of China deal with climate change, position. Based emission price data Guangdong Province from 2015 2021, this paper uses contribution analysis model complete ensemble empirical mode decomposition (CEEMD), particle swarm optimization algorithm-least squares support vector machine (PSO-LSSVM) predict Province. Firstly, are obtained. CEEMD data, filtering noise reduction completed. PSO-LSSVM used for iterative particles obtains optimal solution, each component predicted respectively. Finally, results integrated. shown that: (1) technology improve prediction accuracy IMFs ; (2) parameters LSSVM modeling by PSO algorithm helps select more reasonably avoids randomness artificial selection some extent. research show that applies good generalization ability provides a accurate scheme China.