This is the authors' abstract. We don't add key points for this paper.
This study explores the application of a multi-layer deep neural network to identify green credit risks, with a focus on the role of anti-corruption measures. Using data from 36 Chinese banks, the model incorporates indicators of transparency and accountability to enhance risk prediction. Based on expert judgment and Analytic Hierarchy Process (AHP) analysis, the transparency and accountability indicators were weighted at 0.7 and 0.3, respectively. The model achieved strong performance, maintaining stability under data noise and outperforming traditional methods such as Support Vector Machine (SVM), Convolutional Neural Network (CNN), eXtreme Gradient Boosting (XGBoost), and Deep Belief Network (DBN), with a recall rate of 0.84. Performance improved as the intensity of anti-corruption measures increased, suggesting that governance factors significantly enhance model reliability. These results demonstrate the potential of advanced machine learning techniques in financial risk assessment and emphasize the importance of institutional transparency in promoting sustainable green finance.
Answers are grounded in this paper and cite their sources.
No takes yet. Share an insight, caveat, or question.
Wang et al. (2025) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: