Can Large Language Models Beat Wall Street? Unveiling the Potential of AI in Stock Selection

TL;DR

This paper presents MarketSenseAI, a GPT-4 based framework that uses advanced reasoning and diverse data analysis to outperform traditional stock selection methods, demonstrating significant alpha and returns in empirical tests.

Contribution

Introduces a novel GPT-4 driven framework for stock selection that combines Chain of Thought and In-Context Learning to emulate expert decision-making in finance.

Findings

Achieved 10-30% excess alpha in empirical tests.

Delivered up to 72% cumulative return over 15 months.

Maintained risk profile comparable to the market.

Abstract

This paper introduces MarketSenseAI, an innovative framework leveraging GPT-4's advanced reasoning for selecting stocks in financial markets. By integrating Chain of Thought and In-Context Learning, MarketSenseAI analyzes diverse data sources, including market trends, news, fundamentals, and macroeconomic factors, to emulate expert investment decision-making. The development, implementation, and validation of the framework are elaborately discussed, underscoring its capability to generate actionable and interpretable investment signals. A notable feature of this work is employing GPT-4 both as a predictive mechanism and signal evaluator, revealing the significant impact of the AI-generated explanations on signal accuracy, reliability and acceptance. Through empirical testing on the competitive S&P 100 stocks over a 15-month period, MarketSenseAI demonstrated exceptional performance, delivering excess alpha of 10% to 30% and achieving a cumulative return of up to 72% over the period, while maintaining a risk profile comparable to the broader market. Our findings highlight the transformative potential of Large Language Models in financial decision-making, marking a significant leap in integrating generative AI into financial analytics and investment strategies.