This article reviews the applications, techniques, and insights related to Large Language Models (LLMs) in equity markets, focusing on their potential to disrupt traditional investment strategies through advanced data analysis, market prediction, and automated trading. It synthesizes findings from 84 research studies conducted between 2022 and early 2025, categorizing applications into financial uses such as stock price forecasting, sentiment analysis, and algorithmic trading, while also discussing technical methodologies like prompting, fine-tuning, and multi-agent frameworks. The review highlights both the strengths, such as improved sentiment extraction and the use of reinforcement learning, and critical gaps in scalability, interpretability, and real-world validation, proposing directions for future research that emphasize hybrid modeling approaches and robust evaluation frameworks.
This article reviews the applications, techniques, and insights related to Large Language Models (LLMs) in equity markets, focusing on their potential to disrupt traditional investment strategies through advanced data analysis, market prediction, and automated trading. It synthesizes findings from 84 research studies conducted between 2022 and early 2025, categorizing applications into financial uses such as stock price forecasting, sentiment analysis, and algorithmic trading, while also discussing technical methodologies like prompting, fine-tuning, and multi-agent frameworks. The review highlights both the strengths, such as improved sentiment extraction and the use of reinforcement learning, and critical gaps in scalability, interpretability, and real-world validation, proposing directions for future research that emphasize hybrid modeling approaches and robust evaluation frameworks.