Augmenting Fundamental Analysis with Large Language Models: A RAG-Based System for Generating Investor Briefs

2026-07-10

AI Summary

This study addresses the challenge of efficiently integrating multi-source financial information—including corporate financial reports, macroeconomic indicators, and SEC filings—to support fundamental analysis. To this end, we propose a novel architecture that combines Retrieval-Augmented Generation (RAG) with domain knowledge of Kitchin economic cycles. Leveraging GPT-4o, our system automatically parses EDGAR documents, processes macroeconomic data, and generates personalized investor briefings for nine companies over four consecutive weeks. Notably, this approach is the first to embed macroeconomic cycle modeling within a RAG framework, enabling automated, individualized fundamental analysis tailored to retail investors. Evaluation by nine real-world investors demonstrates that the generated briefings exhibit strong practical utility and analytical effectiveness.

Abstract

In this study, we examine the opportunities brought by Large Language Models (LLMs) to various aspects of fundamental analysis of companies based on their reports as well as data and documents describing macroeconomic situation like GDP and inflation changes as well as documents filled to the U.S. Securities and Exchange Commission (SEC) which can be found in EDGAR. We were preprocessing those data and than sending via API to gpt-4o model in a Retrieval-Augmented Generation (RAG) like regime. We prepared as well a document describing an exemplar investor knowledge based on Kitchin cycles. We were scanning data important for analysis of 9 companies for 4 weeks. Using LLM we were producing automatic briefs about them. They were sent to nine participants who are individual investors to evaluate usefulness of such approach to data analysis.

Problem

• Fundamental Analysis
• Large Language Models
• Investor Briefs
• Retrieval-Augmented Generation
• SEC Filings

Innovation

• Retrieval-Augmented Generation (RAG)
• Large Language Models (LLMs)
• Fundamental Analysis
• Investor Briefs
• Kitchin Cycles