Enhancing the Efficiency and Accuracy of Underlying Asset Reviews in Structured Finance: The Application of Multi-agent Framework

TL;DR

The paper tackles the challenge of due diligence in structured finance by proposing a multi-agent AI framework to automate underlying asset reviews, focusing on cross-verification between loan applications and bank statements in auto ABS. It empirically compares open-source and closed-source LLMs (e.g., GPT-4, LLAMA2, LLAMA3, DBRX) and demonstrates that dual-agent setups can achieve near-perfect accuracy, while also providing a cost analysis that highlights substantial savings over manual review. The findings show AI can reduce manual errors, accelerate processing, and scale to broader financial-document analysis and risk management tasks. This approach has practical implications for efficiency and reliability in financial auditing and regulatory compliance in structured finance.

Abstract

Structured finance, which involves restructuring diverse assets into securities like MBS, ABS, and CDOs, enhances capital market efficiency but presents significant due diligence challenges. This study explores the integration of artificial intelligence (AI) with traditional asset review processes to improve efficiency and accuracy in structured finance. Using both open-sourced and close-sourced large language models (LLMs), we demonstrate that AI can automate the verification of information between loan applications and bank statements effectively. While close-sourced models such as GPT-4 show superior performance, open-sourced models like LLAMA3 offer a cost-effective alternative. Dual-agent systems further increase accuracy, though this comes with higher operational costs. This research highlights AI's potential to minimize manual errors and streamline due diligence, suggesting a broader application of AI in financial document analysis and risk management.

Figures (1)

• Figure 1: The framework in competing the auto loan ABS task.