arXiv：cs.AI· Vedanth Padmaraman, Shreen Anand, Vamshi Vishruth J, Vineet V Pai, Arvind Srinath K. T, Subramanyam Natarajan, Shylaja S S·· 16 小时前
结合 Transformer 金融情绪信号的混合强化学习交易框架
Enhanced Trading Systems with Intelligent Market Analysis
AI 导读
该论文提出一种混合强化学习交易框架，将盘中市场数据与基于 Transformer 的金融情绪信号结合，从财经新闻中提取情绪动态和语义事件簇并注入 PPO 交易智能体。在 NSE 盘中数据上的实验显示，其风险调整后收益优于仅用价格的基线。论文已被 ICAIA 2026 接收。
正文
Abstract:This paper proposes a hybrid reinforcement learning trading framework integrating intraday market data with transformer-based financial sentiment signals. The system extracts sentiment dynamics and semantic event clusters from financial news and incorporates them into a PPO-based trading agent. Experiments on intraday NSE data demonstrate improved risk-adjusted returns compared to price-only baselines.
| Comments: | 9 pages, 1 figure, 2 algorithms, 1 table. Accepted at ICAIA 2026 (proceedings pending) |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| ACM classes: | I.2.6; I.2.1 |
| Cite as: | arXiv:2610.13998 [cs.LG] |
| (or arXiv:2610.13998v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.13998 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Shereen Anand [view email]
[v1]
Sun, 27 Sep 2026 03:53:05 UTC (148 KB)
来源：arXiv：cs.AI · arxiv.org