A TabPFN-Based Framework for Credit Risk Prediction in Automotive Green Supply Chain Finance

As the automotive industry undergoes a green transformation, digital upgrading, and increasingly intensive supply chain collaboration, the supply chain finance credit risks faced by small and medium-sized enterprises (SMEs) in the sector exhibit characteristics such as multi-source interaction, nonlinear transmission, and class imbalance. This study uses 210 SMEs in China’s A-share automotive sector from 2020 to 2024 and constructs a credit risk evaluation system covering 56 indicators across the macro environment, financing enterprises, supply chain characteristics, and core enterprise credit support. Methodologically, DE-LightGBM is employed for feature selection to reduce redundancy and noise, while TabPFGen is introduced to generate synthetic risk-class samples. Business logic constraints and a Nearest Neighbor Distance Ratio filtering mechanism are further applied to improve the plausibility and fidelity of generated samples. Empirical results show that the TabPFN model achieves superior predictive performance after feature selection and data augmentation, and the Wilcoxon signed-rank test confirms the effectiveness and stability of sample augmentation. In addition, the ablation experiment demonstrates that green-related features provide significant incremental predictive value for supply chain finance credit risk identification. The proposed framework provides a useful reference for SME credit assessment, risk early warning, and green financial resource allocation in the automotive industry.