用大模型+强化学习融合新闻情绪与市场数据，提升投资组合收益
FinMarBa: A Market-Informed Dataset for Financial Sentiment Classification
- 分三层架构：基础智能体处理多源数据，元智能体聚合决策，超智能体综合市场与情绪信号
- 2018-2024年回测中年化收益26%，夏普比率达1.2，优于基准和标普500
- 适合量化研究者和金融工程从业者，代码开源可复现
本文提出一种新型分层框架用于投资组合优化，将轻量级大语言模型（LLM）与深度强化学习（DRL）结合，融合金融新闻情绪信号与传统市场指标。三层次架构包括：基础强化学习智能体处理混合数据，元智能体聚合其决策，超智能体根据市场数据与情绪分析整合最终策略。在2018至2024年间的数据上进行评估，训练期为2000-2017年，该框架实现26%的年化收益率与1.2的夏普比率，显著优于等权配置及标普500基准。主要贡献包括可扩展的跨模态融合机制、增强稳定性的分层强化学习结构，以及开源可复现性。
原文摘要 · Abstract (English)
This paper presents a novel hierarchical framework for portfolio optimization, integrating lightweight Large Language Models (LLMs) with Deep Reinforcement Learning (DRL) to combine sentiment signals from financial news with traditional market indicators. Our three-tier architecture employs base RL agents to process hybrid data, meta-agents to aggregate their decisions, and a super-agent to merge decisions based on market data and sentiment analysis. Evaluated on data from 2018 to 2024, after training on 2000-2017, the framework achieves a 26% annualized return and a Sharpe ratio of 1.2, outperforming equal-weighted and S&P 500 benchmarks. Key contributions include scalable cross-modal integration, a hierarchical RL structure for enhanced stability, and open-source reproducibility.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。