中国金融学术研究网

所属栏目：资本市场/市场有效性

Nonlinear Relationships in Stock News Co-Occurrence: A Pairs Trading Test on the Constituent Stocks of the Csi 300 Index Based on Deep Reinforcement Learning Methods

认领作者认领作者管理权限

发布日期：2024年02月25日上次修订日期：2024年02月25日

Jianhe Liu bruceliu@zufe.edu.cn Zhejiang University of Finance and Economics Luze Lu 1344451822@qq.com Zhejiang University of Finance and Economics Xiangyu Zong xyzong@zuel.edu.cn Zhongnan University of Economics and Law Ziping Luo 525030736@qq.com Zhejiang University of Finance and Economics

摘要

We propose a deep reinforcement learning method to improve pairs trading by identifying nonlinear relationships in stock news. Using the CSI 300 index constituents from 2015 to 2022, we integrated cointegration and news co-occurrence analysis in asset pairing and used a threshold-based approach in trading design. Results showed our NEWS-CO-DRL method, fusing deep learning and news co-occurrence, outperformed in return generation and risk control, indicating its potential for the Chinese A-share market.

展开

关键词：

news co-occurrence nonlinear relationships deep reinforcement learning pairs trading

下载论文在线阅读

复制链接

新浪微博

微信扫一扫

论文统计数据

浏览次数：
1909
下载次数：
3

摘要

关键词：

论文统计数据

相关文献