MASCA: LLM based-Multi Agents System for Credit Assessment

TL;DR

This paper introduces MASCA, an innovative multi-agent system powered by large language models that improves credit assessment by mimicking real-world decision processes, integrating contrastive learning, and addressing fairness concerns.

Contribution

The paper presents a novel LLM-driven multi-agent framework for credit evaluation, combining hierarchical architecture, contrastive learning, and theoretical insights from signaling game theory.

Findings

MASCA outperforms baseline methods in credit scoring accuracy.

Hierarchical multi-agent design enhances decision-making effectiveness.

Bias analysis reveals improvements in fairness and bias mitigation.

Abstract

Recent advancements in financial problem-solving have leveraged LLMs and agent-based systems, with a primary focus on trading and financial modeling. However, credit assessment remains an underexplored challenge, traditionally dependent on rule-based methods and statistical models. In this paper, we introduce MASCA, an LLM-driven multi-agent system designed to enhance credit evaluation by mirroring real-world decision-making processes. The framework employs a layered architecture where specialized LLM-based agents collaboratively tackle sub-tasks. Additionally, we integrate contrastive learning for risk and reward assessment to optimize decision-making. We further present a signaling game theory perspective on hierarchical multi-agent systems, offering theoretical insights into their structure and interactions. Our paper also includes a detailed bias analysis in credit assessment, addressing fairness concerns. Experimental results demonstrate that MASCA outperforms baseline approaches, highlighting the effectiveness of hierarchical LLM-based multi-agent systems in financial applications, particularly in credit scoring.