{"title":"基于强化学习框架的投资组合管理","authors":"Wu Junfeng, Li Yaoming, Tan Wenqing, 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, Li Yaoming, Tan Wenqing, 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}
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.
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.