FinMarBa: A Market-Informed Dataset for Financial Sentiment Classification

2025/07/24 by Lefort, Baptiste, Benhamou, Eric, Guez, Beatrice +3
#Computation and Language (cs.CL) #FOS: Computer and information sciences #FOS: Economics and business #General Finance (q-fin.GN)

paper · doi:10.48550/arxiv.2507.22932

Abstract

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.

Citations

• Stress index strategy enhanced with financial news sentiment analysis for the equity markets
• FinBERT: Financial Sentiment Analysis with Pre-trained Language Models
• Good Debt or Bad Debt: Detecting Semantic Orientations in Economic Texts

Related

• HARLF: Hierarchical Reinforcement Learning and Lightweight LLM-Driven Sentiment Integration for Financial Portfolio Optimization
• FinLlama: Financial Sentiment Classification for Algorithmic Trading Applications
• FinSMART: Financial Sentiment Analysis for Algorithmic Trading through Market-Aligned Reinforcement Learning
• Multimodal Deep Reinforcement Learning for Portfolio Optimization
• Financial News-Driven LLM Reinforcement Learning for Portfolio Management