- 期刊
A Reinforcement Learning-Based Portfolio Return Prediction Model
摘要
In this paper, we analyze the price fluctuations of Bitcoin and gold, find the optimal transaction model by establishing the corresponding model, and analyze the transaction cost sensitivity and transaction strategy of transaction risk. Specifically, we employ deep reinforcement learning to simulate trading in stocks. In addition, using the risk analysis of the Sharpe ratio, compared with the Markowitz efficient frontier model of portfolio management, choose a medium risk, high return portfolio. Finally, according to the needs of the trading strategy, the sensitivity analysis of the trading strategy to the transaction cost is completed.
參考文獻
S. Shafiee, E. Topal, An overview of global gold market and gold price forecasting, Resources Policy, 35(3), pp.178-189,2010.
M. Nabipour, P. Nayyeri, H. Jabani, S. S. and A. Mosavi, Predicting stock market trends using machine learning and deep learning algorithms via continuous and binary data; a comparative analysis, in IEEE Access, vol. 8, pp. 150199-150212, 2020, doi: 10.1109/ACCESS.2020.3015966.
C. Zheng and J. Zhu, Research on stock price forecast based on gray relational analysis and ARMAX model, 2017 International Conference on Grey Systems and Intelligent Services (GSIS), 2017, pp. 145-148, doi: 10.1109/GSIS.2017.8077689.
S. Selvin, R. Vinayakumar, E. A. Gopalakrishnan, V. K. Menon and K. P. Soman, Stock price prediction using LSTM, RNN and CNN-sliding window model, 2017 International Conference on Advances in Computing, Communications and Informatics (ICACCI), 2017, pp. 1643-1647,doi: 10.1109/ICACCI.2017.8126078.
I. Letteri, G. D. Penna, G. D. Gasperis, and A. Dyoub, A stock trading system for a medium volatile asset using multi layer perceptron, 2022.