The Role of Artificial Intelligence in Enhancing Credit Risk Management: A Systematic Literature Review of International Banking Systems

Abstract

The integration of Artificial Intelligence (AI) in credit risk management has transformed how financial institutions assess borrower risk, detect fraud, and expand financial inclusion. In this systematic literature review (SLR), we review the state of the art in how AI-based models improve predictive accuracy, mitigate financial risk in international banking systems, and reduce decision-making lead times. This thesis examines how AI can be used in credit scoring, fraud detection, and financial inclusion, and poses regulatory and ethical challenges, including algorithmic bias, data privacy issues, and the intricacy of Explainable AI (XAI). Furthermore, the findings indicate AI models, especially machine learning (ML) and deep learning, can perform better than the traditional credit scoring techniques, concerning the accuracy of default prediction (15%). Furthermore, AI’s combination with blockchain improves fraud detection and cybersecurity, although there are regulations and associated costs to consider. AI similarly enables alternative credit scoring to afford financial access for underserved populations, though fears of bias and data privacy persist. Thus, this review points out why regulatory frameworks such as Basel III and GDPR are necessary for the responsible use of AI. Finally, the study concludes that although benefits can be realised with the adoption of AI, addressing ethical, technical, and regulatory issues is crucial for a sustainable adoption of AI. Future work should include improving XAI, mitigating bias, and enhancing AI-driven credit risk models in view of global financial stability.