The loss given default (LGD) is an important credit risk parameter in the regulatory system for financial institutions. Due to the complex structure of the LGD distribution, we propose a new approach, called the hybrid algorithms multi-stage (HMS) model, to construct a multi-stage LGD prediction model and test it on the US Small Business Administration (SBA)’s small business credit dataset. We then compare the model’s performance under four routes by different evaluation metrics. Finally, pertinent business information and macroeconomic features datasets are added for robustness validation. The results show that HMS performs well and stably for predicting LGD, confirming the superiority of the proposed hybrid unsupervised and supervised machine learning algorithm. Financial institutions can apply the approach to make default predictions based on other credit datasets.

Purpose: We investigate the impact of climate policy uncertainty (CPU) on bank asset quality (BAQ) in the context of Chinese commercial banks. Design/methodology/approach: Using quarterly panel data from A-share listed commercial banks in China from 2008 to 2022, we employ fixed-effects regression models to examine the relationship between CPU and BAQ, measured by the non-performing loans to total loans ratio (NPL). We also explore the moderating effects of capital adequacy, corporate governance and digital transformation. Findings/results: The results reveal that CPU significantly increases NPL, thereby weakening asset quality, with variations observed across different bank types and sizes. In addition, a higher capital adequacy ratio (CAR), enhanced corporate governance and improved digital transformation capabilities help mitigate the negative effects of CPU on BAQ. Practical implications: The findings suggest that bankers should develop differentiated climate risk response strategies and bolster resilience to address the CPU. Policymakers are encouraged to enhance the foresight and stability of climate policies to lessen the impact of CPU on financial institutions. Originality/value: This study enriches the understanding of climate financial risks by identifying CPU as a critical external factor affecting bank stability. It offers new insights into how internal governance mechanisms and digital capabilities can buffer the effects of climate-related uncertainties in the banking sector.