Research on machine learning in credit risk management: current developments and future trends

The study focuses on the critical role of credit risk management in the financial system, particularly as financial crises become more frequent and complex financial instruments spread. Traditional credit risk assessment methods struggle to address dynamic market changes. With the advancement of artificial intelligence, especially machine learning, credit risk management is gaining new opportunities. Machine learning algorithms can process large volumes of data, enabling more accurate identification of potential default risks. This study aims to systematically analyze the current applications and future trends of machine learning in credit risk management using bibliometric methods.The research uses bibliometric analysis tools such as CiteSpace and VOSviewer to visualize data from 621 relevant papers between 2014 and 2024 from the Web of Science. By examining keyword bursts, author collaborations, and national collaboration networks, the study highlights research hotspots, primary application scenarios, and current gaps in using machine learning for credit risk management. The findings indicate that machine learning techniques, particularly support vector machines, neural networks, and deep learning, have been widely applied in credit risk prediction in recent years, but comparative studies between algorithms are lacking. While big data technologies are gaining attention, their integration with machine learning remains insufficient. This study fills this gap and suggests future research directions. The study offers significant theoretical and practical value, providing a comprehensive literature review for academia and theoretical support for financial institutions to optimize credit risk management.