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

TL;DR

This paper investigates how integrating AI, especially large language models, into structured finance asset reviews can improve efficiency and accuracy, reducing manual errors and streamlining due diligence processes.

Contribution

It introduces a multi-agent AI framework combining open-source and closed-source LLMs to automate and enhance asset review accuracy in structured finance.

Findings

AI automates verification between loan applications and bank statements.

Close-sourced models like GPT-4 outperform open-source models in accuracy.

Dual-agent systems increase review accuracy at higher operational costs.

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.