Reproduce “Integrating Large Language Models in Financial Investments and Market Analysis: A Survey” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Sedigheh Mahdavi, Jiating, Chen, Pradeep Kumar Joshi, Lina Huertas Guativa, Upmanyu Singh
This survey paper provides a structured overview of recent research on integrating Large Language Models (LLMs) into financial investments and market analysis, categorizing diverse contributions into four frameworks. It reviews LLM applications across tasks like stock selection, risk assessment, and trading, while identifying current capabilities and future research directions in this rapidly evolving field.
Key insights
- LLMs offer transformative potential by effectively processing and understanding both structured and unstructured financial data, going beyond the limitations of traditional methods.
- Various architectural strategies are emerging, from end-to-end LLM-driven systems to hybrid models combining LLMs with traditional finance techniques and multi-agent systems.
- Domain-specific fine-tuning and adaptation (e.g., LoRA) are crucial for specializing general-purpose LLMs to financial contexts, leading to more accurate and contextually relevant outputs.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.