LLMDE: A Large Language Model-Driven Differential Evolution Algorithm for Portfolio Optimization

2026-09-15

AI Summary

研究提出了一种基于大型语言模型驱动的差分进化算法（LLMDE），通过优化反馈动态选择变异策略和配置控制参数，以解决投资组合优化问题。

Abstract

This study proposes a Large Language Model-Driven Differential Evolution (LLMDE) algorithm to reduce the reliance on handcrafted hyperparameter design. The proposed algorithm leverages a prompt engineering strategy, allowing large language models (LLMs) to dynamically select mutation strategies and configure control parameters guided by optimization feedback, thus enhancing the performance of the DE algorithm. We evaluate the performance of LLMDE on the CEC2022 benchmark suite, comparing it with standard DE and representative metaheuristics. Furthermore, we employ factor analysis and K-means clustering for stock selection, and then apply LLMDE to solve the Conditional Value at Risk (CVaR) portfolio optimization problem using the selected stocks, subject to budget and minimum expected return constraints. Experimental results demonstrate that LLMDE achieves competitive performance on the benchmark suite while continuously generating high-quality solutions for complex constrained optimization tasks. These outcomes successfully demonstrate the viability of embedding LLMs within metaheuristics, paving a promising path toward the design of advanced LLM-assisted optimization techniques.

Problem

• Portfolio Optimization
• Differential Evolution
• Large Language Models
• Hyperparameter Design
• Conditional Value at Risk

Innovation

• Large Language Model-Driven
• Differential Evolution
• Prompt Engineering Strategy
• Optimization Feedback
• Portfolio Optimization