MarketSenseAI 2.0: Enhancing Stock Analysis through LLM Agents

TL;DR

This paper tackles the challenge of integrating heterogeneous financial data streams (news, fundamentals, macro indicators) into a coherent, transparent stock-analysis framework using Large Language Models. It presents MarketSenseAI, featuring a Chain-of-Agents architecture and HyDE-enhanced Retrieval-Augmented Generation to process SEC filings, earnings calls, macro reports, and market data, with empirical validation on S&P 100 and S&P 500 stocks. The key contributions include a granular three-layer Fundamentals analysis, a macro-focused RAG module, and extensive backtesting showing superior cumulative returns and favorable risk-adjusted metrics relative to benchmarks. The work advances practical AI-driven investment analytics by enabling robust, explainable, and scalable analysis across large stock universes, with clear paths for future enhancements and broader deployment.

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.

Figures (7)

• Figure 1: Conceptual Architecture of MarketSenseAI, highlighting for a selected stock (i.e., Nvidia on Jan. 3, 2025). The agents' outputs have been condensed for illustration purposes.
• Figure 2: Fundamentals Agent architecture. Processes in red boxes depict the new processes responsible for integrating the company notes and disclosures from SEC filings and insights from earning call's press conference.
• Figure 3: Analysis of Fundamentals Agent's sentiment output: (a) histogram distribution and (b) scatter plot comparison. Points below the line indicate cases where sentiment improved after incorporating filings and earnings call data.
• Figure 4: Analysis of Signal Agent's sentiment output: (a) histogram distribution and (b) scatter plot comparison. Points in the yellow and green boxes indicate cases where the incorporation of filings and earnings call data results in a change of the stock signal.
• Figure 5: Macroeconomic Agent's functions during data injection.