EFS: Evolutionary Factor Searching for Sparse Portfolio Optimization Using Large Language Models

TL;DR

This paper introduces EFS, a novel framework that uses large language models and evolutionary algorithms to generate and refine alpha factors for sparse portfolio optimization, outperforming traditional methods in diverse market conditions.

Contribution

EFS is the first framework to leverage LLMs for automated alpha factor generation and evolution in portfolio optimization, integrating language guidance with evolutionary feedback.

Findings

EFS outperforms traditional statistical and optimization baselines.

EFS performs well in large asset universes and volatile markets.

Ablation studies confirm the importance of prompt design and factor diversity.

Abstract

Sparse portfolio optimization is a fundamental yet challenging problem in quantitative finance, since traditional approaches heavily relying on historical return statistics and static objectives can hardly adapt to dynamic market regimes. To address this issue, we propose Evolutionary Factor Search (EFS), a novel framework that leverages large language models (LLMs) to automate the generation and evolution of alpha factors for sparse portfolio construction. By reformulating the asset selection problem as a top-m ranking task guided by LLM-generated factors, EFS incorporates an evolutionary feedback loop to iteratively refine the factor pool based on performance. Extensive experiments on five Fama-French benchmark datasets and three real-market datasets (US50, HSI45 and CSI300) demonstrate that EFS significantly outperforms both statistical-based and optimization-based baselines, especially in larger asset universes and volatile conditions. Comprehensive ablation studies validate the importance of prompt composition, factor diversity, and LLM backend choice. Our results highlight the promise of language-guided evolution as a robust and interpretable paradigm for portfolio optimization under structural constraints.