Comparing Credit Risk Estimates in the Gen-AI Era

TL;DR

This paper compares traditional credit risk modeling methods with generative AI approaches, finding that current generative AI models underperform traditional techniques in credit scoring tasks, indicating the need for further research.

Contribution

It provides a comparative analysis highlighting the limitations of current generative AI models in credit risk estimation compared to traditional methods.

Findings

Generative AI models underperform traditional credit scoring methods.

Current generative AI approaches are not yet suitable for credit risk modeling.

Further research is needed to improve generative AI for credit scoring.

Abstract

Generative AI technologies have demonstrated significant potential across diverse applications. This study provides a comparative analysis of credit score modeling techniques, contrasting traditional approaches with those leveraging generative AI. Our findings reveal that current generative AI models fall short of matching the performance of traditional methods, regardless of the integration strategy employed. These results highlight the limitations in the current capabilities of generative AI for credit risk scoring, emphasizing the need for further research and development before the possibility of applying generative AI for this specific task, or equivalent ones.