Predicting Corporate Carbon Disclosure in China: Evidence from Interpretable Machine Learning

Corporate carbon disclosure has become increasingly important in China’s transition toward sustainability and low-carbon development, yet existing research often focuses on isolated determinants and relies mainly on linear empirical models. Using 48,187 observations of Chinese A-share firms from 2012 to 2024, this study identifies the key predictors of corporate carbon disclosure. It develops an interpretable machine learning model and compares its predictive performance with that of linear regression, LASSO, decision tree, random forest, support vector machine, GBDT, and XGBoost. The results show that ensemble methods outperform linear models in both in-sample and out-of-sample predictions. GBDT delivers the best out-of-sample performance, with an R2 of 0.5191, suggesting that nonlinear relationships and interaction effects matter in predicting corporate carbon disclosure. The key factors identified are firm size, media attention, environmental policy intensity, market concentration, and executive financial background. The heterogeneity tests show that regulatory and governance factors are more important for firms in heavily polluting industries, state-owned firms, and firms in central and western China, whereas market factors are more important for firms in eastern China, private firms, and firms in less polluting industries. Overall, the paper provides new evidence on the prediction of corporate carbon disclosure and offers practical implications for regulators and firms seeking to improve their sustainability-related disclosure practices.