Large Language Models in Equity Markets: Applications, Techniques, and Insights
Comprehensive review of 84 studies on large language models in equity markets, analyzing applications, techniques, innovations, limitations, and future directions.
What it examines
This survey reviews recent studies on applying large language models in equity markets. It categorizes methods like prompting, fine-tuning, multi-agent systems, and reinforcement learning for tasks such as stock forecasting, sentiment analysis, and portfolio management. The study maps trends, explores technical innovations, and identifies research gaps in finance.
What it concludes
The findings indicate that LLMs can enhance stock forecasting, trading automation, and financial analysis by integrating structured and unstructured data. However, limitations in real-world testing and explainability remain. Future research should improve hybrid models, computational efficiency, and expand applications to broader financial instruments and regions.
Evidence objects
Survey reveals LLMs rapidly reshape equity markets by blending structured and unstructured data, enhancing prediction accuracy and decision-making through innovative quantitative methods combined with prompting, fine-tuning, reinforcement learning, and systems.
key_findings bullet 1 · key_findings · validation V0
Researchers integrate qualitative news insights by converting them into numerical signals, powering stock trend prediction through frameworks like Ploutos, StockTime, and benchmarks such as InvestorBench, despite scalability and interpretability challenges.
key_findings bullet 2 · key_findings · validation V0
The review of 84 studies introduces hybrid modeling and knowledge generation prompting, highlighting significant strengths and limitations while charting LLMs' disruptive potential and prompting future improvements across global financial ecosystems.
key_findings bullet 3 · key_findings · validation V0
This paper innovatively fuses large language models with equity market analysis, synthesizing and categorizing research trends into a dual framework. Its novelty lies in bridging AI with quantitative finance, offering fresh perspectives for professionals despite its review nature. The work remains engaging, relevant, and valuable for practitioners seeking market insights.
key_findings bullet 4 · key_findings · validation V0
Raw abstract and provenance
- … analysis, market prediction, and automated trading. This … and other reinforcement learning AI techniques into their … of LLM-driven strategies becomes crucial. This paper …
Source row: 1165 · abstract type: snippet