An interval-valued carbon price prediction model based on improved multi-scale feature selection and optimal multi-kernel support vector regression

Precise carbon price prediction is crucial for informing climate policies, maintaining carbon markets, and driving global green transformation. Currently, decomposition integration methods are extensively employed for carbon price forecasting. However, most studies focus on predicting single values, neglecting the inherent volatility and uncertainty of interval-valued data. To address this gap, this study introduces an advanced interval-valued decomposition integration model that incorporates data preprocessing, improved multi-scale feature selection, and data-driven prediction technique. Initially, data preprocessing transforms the maximum and minimum carbon prices into central and radius sequences, capturing greater volatility information while eliminating noise and managing outliers. Subsequently, improved variational mode decomposition is utilized to optimally decompose and reconstruct the center and radius series, which enables a deeper exploration of the features of interval-valued data. A tailored data-driven prediction method is then employed to analyze sub-sequences with distinct characteristics separately, significantly reducing prediction errors. To assess the reliability and stability of the proposed model, a comprehensive comparative experiment is conducted, with results providing strong evidence supporting its effectiveness.