Chain-of-Alpha: Unleashing the Power of Large Language Models for Alpha Mining in Quantitative Trading

2025-08-08

AI Summary

This paper addresses three key challenges in quantitative trading: heavy reliance on manual labor for alpha factor discovery, poor interpretability, and limited generalization capability. To tackle these issues, we propose Chain-of-Alpha—a novel dual-chain framework powered by large language models (LLMs). It comprises a factor generation chain that automatically synthesizes formulaic alpha expressions, and an optimization chain that iteratively refines them using backtesting feedback and domain-specific financial priors. The framework enables end-to-end automated alpha discovery without human intervention, ensuring both interpretability and scalability. Empirical evaluation on the real-world A-share market demonstrates that factors generated by Chain-of-Alpha significantly outperform traditional methods and state-of-the-art LLM-based baselines across critical metrics—including information coefficient (IC), information ratio (IR), and Sharpe ratio—validating the effectiveness and practicality of LLM-driven automated alpha mining.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Search and Optimization: Algorithm Configuration
• Natural Language Processing: (Large) Language Models

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

Alpha factor mining is a fundamental task in quantitative trading, aimed at discovering interpretable signals that can predict asset returns beyond systematic market risk. While traditional methods rely on manual formula design or heuristic search with machine learning, recent advances have leveraged Large Language Models (LLMs) for automated factor discovery. However, existing LLM-based alpha mining approaches remain limited in terms of automation, generality, and efficiency. In this paper, we propose Chain-of-Alpha, a novel, simple, yet effective and efficient LLM-based framework for fully automated formulaic alpha mining. Our method features a dual-chain architecture, consisting of a Factor Generation Chain and a Factor Optimization Chain, which iteratively generate, evaluate, and refine candidate alpha factors using only market data, while leveraging backtest feedback and prior optimization knowledge. The two chains work synergistically to enable high-quality alpha discovery without human intervention and offer strong scalability. Extensive experiments on real-world A-share benchmarks demonstrate that Chain-of-Alpha outperforms existing baselines across multiple metrics, presenting a promising direction for LLM-driven quantitative research.

Problem

• Automating alpha factor mining in quantitative trading
• Enhancing LLM-based alpha discovery without human intervention
• Improving efficiency and scalability of formulaic alpha generation

Innovation

• Dual-chain architecture for alpha mining
• Automated factor generation and optimization
• LLM-driven without human intervention