News-Aware Direct Reinforcement Trading for Financial Markets

TL;DR

This paper introduces a news-aware reinforcement learning approach for financial trading that leverages large language model-derived sentiment scores and raw data, demonstrating superior performance in cryptocurrency markets without handcrafted features.

Contribution

It presents an end-to-end reinforcement learning framework incorporating news sentiment directly, avoiding manual feature engineering, and shows its effectiveness in cryptocurrency trading.

Findings

Outperforms market benchmarks in cryptocurrency trading.

Highlights importance of time-series data in reinforcement learning.

Demonstrates effectiveness of large language model sentiment scores.

Abstract

The financial market is known to be highly sensitive to news. Therefore, effectively incorporating news data into quantitative trading remains an important challenge. Existing approaches typically rely on manually designed rules and/or handcrafted features. In this work, we directly use the news sentiment scores derived from large language models, together with raw price and volume data, as observable inputs for reinforcement learning. These inputs are processed by sequence models such as recurrent neural networks or Transformers to make end-to-end trading decisions. We conduct experiments using the cryptocurrency market as an example and evaluate two representative reinforcement learning algorithms, namely Double Deep Q-Network (DDQN) and Group Relative Policy Optimization (GRPO). The results demonstrate that our news-aware approach, which does not depend on handcrafted features or manually designed rules, can achieve performance superior to market benchmarks. We further highlight the critical role of time-series information in this process.