MarketSenseAI 2.0: Enhancing Stock Analysis through LLM Agents

2025-02-01

AI Summary

Integrating heterogeneous, multi-source financial information—such as SEC filings, earnings call transcripts, financial news, macroeconomic reports, and market data—remains challenging in equity investment due to semantic misalignment and limited interpretability. Method: This paper proposes a retrieval-augmented, multi-role LLM agent framework that synergistically combines structured financial document parsing, dynamic risk-aware modeling, and RAG-driven collaborative reasoning to enable end-to-end fundamental analysis and stock selection. Contribution/Results: Evaluated on the S&P 100 over a two-year backtest, the framework achieves a cumulative return of 125.9% (versus 73.5% for the benchmark), and on the S&P 500, it improves the Sortino ratio by 33.8%. The approach significantly enhances analytical robustness and decision interpretability through transparent, evidence-grounded reasoning grounded in authoritative financial sources.

Technology Category

• Multiagent Systems: Mechanism Design
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

MarketSenseAI is a novel framework for holistic stock analysis which leverages Large Language Models (LLMs) to process financial news, historical prices, company fundamentals and the macroeconomic environment to support decision making in stock analysis and selection. In this paper, we present the latest advancements on MarketSenseAI, driven by rapid technological expansion in LLMs. Through a novel architecture combining Retrieval-Augmented Generation and LLM agents, the framework processes SEC filings and earnings calls, while enriching macroeconomic analysis through systematic processing of diverse institutional reports. We demonstrate a significant improvement in fundamental analysis accuracy over the previous version. Empirical evaluation on S&P 100 stocks over two years (2023-2024) shows MarketSenseAI achieving cumulative returns of 125.9% compared to the index return of 73.5%, while maintaining comparable risk profiles. Further validation on S&P 500 stocks during 2024 demonstrates the framework's scalability, delivering a 33.8% higher Sortino ratio than the market. This work marks a significant advancement in applying LLM technology to financial analysis, offering insights into the robustness of LLM-driven investment strategies.

Problem

• Stock Investment Optimization
• Financial Data Analysis
• Investment Strategy Improvement

Innovation

• AI-enhanced analysis
• SEC filings
• outperforms traditional investment methods