基于强化学习框架的投资组合管理

IF 3.4 3区 经济学 Q1 ECONOMICS Journal of Forecasting Pub Date : 2024-05-19 DOI:10.1002/for.3155
Wu Junfeng, Li Yaoming, Tan Wenqing, Chen Yun
{"title":"基于强化学习框架的投资组合管理","authors":"Wu Junfeng,&nbsp;Li Yaoming,&nbsp;Tan Wenqing,&nbsp;Chen Yun","doi":"10.1002/for.3155","DOIUrl":null,"url":null,"abstract":"<p>Portfolio management is crucial for investors. We propose a dynamic portfolio management framework based on reinforcement learning using the proximal policy optimization algorithm. The two-part framework includes a feature extraction network and a full connected network. First, the majority of the previous research on portfolio management based on reinforcement learning has been dedicated to discrete action spaces. We propose a potential solution to the problem of a continuous action space with a constraint (i.e., the sum of the portfolio weights is equal to 1). Second, we explore different feature extraction networks (i.e., convolutional neural network [CNN], long short-term memory [LSTM] network, and convolutional LSTM network) combined with our system, and we conduct extensive experiments on the six kinds of assets, including 16 features. The empirical results show that the CNN performs best in the test set. Last, we discuss the effect of the trading frequency on our trading system and find that the monthly trading frequency has a higher Sharpe ratio in the test set than other trading frequencies.</p>","PeriodicalId":47835,"journal":{"name":"Journal of Forecasting","volume":null,"pages":null},"PeriodicalIF":3.4000,"publicationDate":"2024-05-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Portfolio management based on a reinforcement learning framework\",\"authors\":\"Wu Junfeng,&nbsp;Li Yaoming,&nbsp;Tan Wenqing,&nbsp;Chen Yun\",\"doi\":\"10.1002/for.3155\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p>Portfolio management is crucial for investors. We propose a dynamic portfolio management framework based on reinforcement learning using the proximal policy optimization algorithm. The two-part framework includes a feature extraction network and a full connected network. First, the majority of the previous research on portfolio management based on reinforcement learning has been dedicated to discrete action spaces. We propose a potential solution to the problem of a continuous action space with a constraint (i.e., the sum of the portfolio weights is equal to 1). Second, we explore different feature extraction networks (i.e., convolutional neural network [CNN], long short-term memory [LSTM] network, and convolutional LSTM network) combined with our system, and we conduct extensive experiments on the six kinds of assets, including 16 features. The empirical results show that the CNN performs best in the test set. Last, we discuss the effect of the trading frequency on our trading system and find that the monthly trading frequency has a higher Sharpe ratio in the test set than other trading frequencies.</p>\",\"PeriodicalId\":47835,\"journal\":{\"name\":\"Journal of Forecasting\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":3.4000,\"publicationDate\":\"2024-05-19\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Forecasting\",\"FirstCategoryId\":\"96\",\"ListUrlMain\":\"https://onlinelibrary.wiley.com/doi/10.1002/for.3155\",\"RegionNum\":3,\"RegionCategory\":\"经济学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"ECONOMICS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Forecasting","FirstCategoryId":"96","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1002/for.3155","RegionNum":3,"RegionCategory":"经济学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ECONOMICS","Score":null,"Total":0}
引用次数: 0

摘要

投资组合管理对投资者至关重要。我们提出了一种基于强化学习的动态投资组合管理框架,使用近似策略优化算法。该框架由两部分组成,包括特征提取网络和全连接网络。首先,以往基于强化学习的投资组合管理研究大多针对离散行动空间。我们针对带有约束条件(即组合权重之和等于 1)的连续行动空间问题提出了一种潜在的解决方案。其次,我们探索了不同特征提取网络(即卷积神经网络[CNN]、长短期记忆[LSTM]网络和卷积 LSTM 网络)与系统的结合,并对包括 16 个特征在内的 6 种资产进行了大量实验。实证结果表明,CNN 在测试集中表现最佳。最后,我们讨论了交易频率对交易系统的影响,发现在测试集中,月度交易频率的夏普比率高于其他交易频率。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Portfolio management based on a reinforcement learning framework

Portfolio management is crucial for investors. We propose a dynamic portfolio management framework based on reinforcement learning using the proximal policy optimization algorithm. The two-part framework includes a feature extraction network and a full connected network. First, the majority of the previous research on portfolio management based on reinforcement learning has been dedicated to discrete action spaces. We propose a potential solution to the problem of a continuous action space with a constraint (i.e., the sum of the portfolio weights is equal to 1). Second, we explore different feature extraction networks (i.e., convolutional neural network [CNN], long short-term memory [LSTM] network, and convolutional LSTM network) combined with our system, and we conduct extensive experiments on the six kinds of assets, including 16 features. The empirical results show that the CNN performs best in the test set. Last, we discuss the effect of the trading frequency on our trading system and find that the monthly trading frequency has a higher Sharpe ratio in the test set than other trading frequencies.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
CiteScore
5.40
自引率
5.90%
发文量
91
期刊介绍: The Journal of Forecasting is an international journal that publishes refereed papers on forecasting. It is multidisciplinary, welcoming papers dealing with any aspect of forecasting: theoretical, practical, computational and methodological. A broad interpretation of the topic is taken with approaches from various subject areas, such as statistics, economics, psychology, systems engineering and social sciences, all encouraged. Furthermore, the Journal welcomes a wide diversity of applications in such fields as business, government, technology and the environment. Of particular interest are papers dealing with modelling issues and the relationship of forecasting systems to decision-making processes.
期刊最新文献
Issue Information Issue Information Predictor Preselection for Mixed‐Frequency Dynamic Factor Models: A Simulation Study With an Empirical Application to GDP Nowcasting Deep Dive Into Churn Prediction in the Banking Sector: The Challenge of Hyperparameter Selection and Imbalanced Learning Demand Forecasting New Fashion Products: A Review Paper
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1