Automate Strategy Finding with LLM in Quant Investment
This work addresses the problem of unreliable automated trading strategies for quantitative investors by extending LLMs to financial applications, though it appears incremental as it adapts existing LLM techniques to a specific domain.
The paper tackles the brittleness of traditional deep learning models in quantitative finance by developing a three-stage LLM-based framework for automated strategy finding, achieving a 53.17% cumulative return on SSE50 from January 2023 to January 2024 and outperforming benchmarks in Chinese and US markets.
We present a novel three-stage framework leveraging Large Language Models (LLMs) within a risk-aware multi-agent system for automate strategy finding in quantitative finance. Our approach addresses the brittleness of traditional deep learning models in financial applications by: employing prompt-engineered LLMs to generate executable alpha factor candidates across diverse financial data, implementing multimodal agent-based evaluation that filters factors based on market status, predictive quality while maintaining category balance, and deploying dynamic weight optimization that adapts to market conditions. Experimental results demonstrate the robust performance of the strategy in Chinese & US market regimes compared to established benchmarks. Our work extends LLMs capabilities to quantitative trading, providing a scalable architecture for financial signal extraction and portfolio construction. The overall framework significantly outperforms all benchmarks with 53.17% cumulative return on SSE50 (Jan 2023 to Jan 2024), demonstrating superior risk-adjusted performance and downside protection on the market.