A Deep Reinforcement Learning-Based Decision Support System for Automated Stock Market Trading

被引:6
|
作者
Ansari, Yasmeen [1 ]
Yasmin, Sadaf [2 ]
Naz, Sheneela [3 ]
Zaffar, Hira [4 ]
Ali, Zeeshan [5 ]
Moon, Jihoon [6 ]
Rho, Seungmin [7 ]
机构
[1] Saudi Elect Univ, Coll Adm & Financial Sci, Dept Finance, Riyadh 13323, Saudi Arabia
[2] COMSATS Univ Islamabad, Dept Comp Sci, Attock Campus, Attock 43600, Pakistan
[3] COMSATS Univ Islamabad, Dept Comp Sci, Islamabad 45550, Pakistan
[4] Air Univ, Dept Comp Sci, Aerosp & Aviat Kamra Campus, Islamabad 44000, Pakistan
[5] Natl Univ Comp & Emerging Sci, Res & Dev Setups, Islamabad 44000, Pakistan
[6] Soonchunhyang Univ, Dept AI & Big Data, Asan 31538, South Korea
[7] Chung Ang Univ, Dept Ind Secur, Seoul 06974, South Korea
关键词
Decision support system; automated stock trading; deep reinforcement learning; deep-Q networks; forecasting network; GRU; long-term market future patterns; NEURAL-NETWORKS; RULE DISCOVERY; RECOGNITION;
D O I
10.1109/ACCESS.2022.3226629
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Presently, the volatile and dynamic aspects of stock prices are significant research challenges for stock markets or any other financial sector to design accurate and profitable trading strategies in all market situations. To meet such challenges, the usage of computer-aided stock trading techniques has grown in prominence in recent decades owing to their ability to rapidly and accurately analyze stock market situations. In the recent past, deep reinforcement learning (DRL) methods and trading bots are commonly utilized for algorithmic trading. However, in the existing literature, the trading agents employ the historical and present trends of stock prices as an observing state to make trading decisions without taking into account the long-term market future pattern of stock prices. Therefore, in this study, we proposed a novel decision support system for automated stock trading based on deep reinforcement learning that observes both past and future trends of stock prices whether single and multi-step ahead as an observing state to make the optimal trading decisions of buying, selling, and holding the stocks. More specifically, at every time step, future trends are monitored concurrently using a forecasting network whose output is concatenated with past trends of stock prices. The concatenated vectors are subsequently supplied to the DRL agent as an observation state. In addition, the suggested forecasting network is built on a Gated Recurrent Unit (GRU). The GRU-based agent captures more informative and inherent aspects of time-series financial data. Furthermore, the suggested decision support system has been tested on several stock markets such as Tesla, IBM, Amazon, CSCO, and Chinese Stocks as well as equity markets i-e SSE Composite Index, NIFTY 50 Index, US Commodity Index Fund, and has achieved encouraging profit values while trading.
引用
收藏
页码:127469 / 127501
页数:33
相关论文
共 50 条
  • [1] Quantitative Trading on Stock Market Based on Deep Reinforcement Learning
    Wu, Jia
    Wang, Chen
    Xiong, Lidong
    Sun, Hongyong
    [J]. 2019 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2019,
  • [2] Beating the Stock Market with a Deep Reinforcement Learning Day Trading System
    Conegundes, Leonardo
    Machado Pereira, Adriano C.
    [J]. 2020 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2020,
  • [3] Application of Deep Reinforcement Learning on Automated Stock Trading
    Chen, Lin
    Gao, Qiang
    [J]. PROCEEDINGS OF 2019 IEEE 10TH INTERNATIONAL CONFERENCE ON SOFTWARE ENGINEERING AND SERVICE SCIENCE (ICSESS 2019), 2019, : 29 - 33
  • [4] LSTM based decision support system for swing trading in stock market
    Banik, Shouvik
    Sharma, Nonita
    Mangla, Monika
    Shitharth, S.
    Mohanty, Sachi Nandan
    [J]. KNOWLEDGE-BASED SYSTEMS, 2022, 239
  • [5] Deep Reinforcement Learning Approach for Trading Automation in the Stock Market
    Kabbani, Taylan
    Duman, Ekrem
    [J]. IEEE ACCESS, 2022, 10 : 93564 - 93574
  • [6] Evolutionary decision support system for stock market trading
    Lipinski, Piotr
    [J]. ARTIFICIAL INTELLIGENCE: METHODOLOGY, SYSTEMS, AND APPLICATIONS, 2008, 5253 : 405 - 409
  • [7] Stock Market Trading Based on Market Sentiments and Reinforcement Learning
    Suhail, K. M. Ameen
    Sankar, Syam
    Kumar, Ashok S.
    Nestor, Tsafack
    Soliman, Naglaa F.
    Algarni, Abeer D.
    El-Shafai, Walid
    Abd El-Samie, Fathi E.
    [J]. CMC-COMPUTERS MATERIALS & CONTINUA, 2022, 70 (01): : 935 - 950
  • [8] A novel Deep Reinforcement Learning based automated stock trading system using cascaded LSTM networks
    Zou, Jie
    Lou, Jiashu
    Wang, Baohua
    Liu, Sixue
    [J]. EXPERT SYSTEMS WITH APPLICATIONS, 2024, 242
  • [9] A novel Deep Reinforcement Learning based automated stock trading system using cascaded LSTM networks
    Zou, Jie
    Lou, Jiashu
    Wang, Baohua
    Liu, Sixue
    [J]. Expert Systems with Applications, 2024, 242
  • [10] Machine Learning-Based Decision-Making for Stock Trading: Case Study for Automated Trading in Saudi Stock Exchange
    Alsulmi, Mohammad
    A-Shahrani, Nourah
    [J]. SCIENTIFIC PROGRAMMING, 2022, 2022