CreditXAI: A Multi-Agent System for Explainable Corporate Credit Rating

TL;DR

CreditXAI introduces a multi-agent system that enhances interpretability and accuracy in corporate credit rating by simulating analyst collaboration across risk dimensions, outperforming traditional deep learning models.

Contribution

The paper presents a novel multi-agent framework that models collaborative decision-making for credit ratings, addressing interpretability and accuracy limitations of existing methods.

Findings

Predictive accuracy improves by over 7% with multi-agent collaboration.

The framework offers a more interpretable and comprehensive credit assessment.

Experimental results validate the effectiveness of the proposed system.

Abstract

In the domain of corporate credit rating, traditional deep learning methods have improved predictive accuracy but still suffer from the inherent 'black-box' problem and limited interpretability. While incorporating non-financial information enriches the data and provides partial interpretability, the models still lack hierarchical reasoning mechanisms, limiting their comprehensive analytical capabilities. To address these challenges, we propose CreditXAI, a Multi-Agent System (MAS) framework that simulates the collaborative decision-making process of professional credit analysts. The framework focuses on business, financial, and governance risk dimensions to generate consistent and interpretable credit assessments. Experimental results demonstrate that multi-agent collaboration improves predictive accuracy by more than 7% over the best single-agent baseline, confirming its significant synergistic advantage in corporate credit risk evaluation. This study provides a new technical pathway to build intelligent and interpretable credit rating models.