Welcome to Francis Academic Press

Academic Journal of Computing & Information Science, 2022, 5(10); doi: 10.25236/AJCIS.2022.051010.

Research on Stock Trading Strategy Based on Deep Reinforcement Learning


Li Tan1, Shuqi Liang2 

Corresponding Author:
Li Tan

1School of Information Management, Xinjiang University of Finance and Economics, Urumchi, 830000, China.

2School of Information Engineering, Zhujiang College, South China Agricultural University, Guangzhou, 510900, China.


The stock market occupies an important position in the country's overall economic system, and changes in the stock market affect the investment returns of investors and investment institutions. With the advancement of science and technology and the development of the economic market, the price trend of stocks is disturbed by more and more factors, and the traditional forecasting method is becoming more and more difficult to meet people's requirements. Among them, the stock price time series as a dynamic, irregular, non-linear, non-parameterized complex data, brings great challenges to stock price prediction, so The study proposed to use CNN and LSTM models to predict stock prices. First, the data features are extracted using the CNN network structure, and then the stock price is predicted using LSTM. Experiments have proved that the model can be successfully applied to the study of stock forecasting and has a high accuracy in forecasting.


CNN; LSTM; Stock forecasts

Cite This Paper

Li Tan, Shuqi Liang. Research on Stock Trading Strategy Based on Deep Reinforcement Learning. Academic Journal of Computing & Information Science (2022), Vol. 5, Issue 10: 60-65. https://doi.org/10.25236/AJCIS.2022.051010.


[1] Wang D, Wang X P, Yang C D. A Study of Stock Forecasting Based on LSTM Model of Principal Component Analysis [J]. Journal of Chongqing University of Technology (Natural Science), 2021, 35(2): 282-288.

[2] Liu H. Research on Chinese stock trend prediction model based on LSTM-CNN [D]. Xiamen University, 2019.

[3] Shen Shanshan, Li Qiumin. Short-term stock price prediction by CNN-LSTM based on attention mechanism [J]. Software, 2022,43(02):73-75.

[4] Zhou Zhihua. Machine Learning [J]. Aviation Port, 2018, (02): 94.

[5] Chen Q. Q. Studying stock price movements based on CNN-LSTM neural networks [J]. Journal of Economic Research, 2020, (02): 157-160.

[6] Luo Xiaoting. Research on deep learning-based stock risk prediction methods [J]. Time Finance, 2022, (02): 30-32.

[7] Cao Chaofan, Luo Zenan, Xie Jiaxin, Li Lu. Research on MDT-CNN-LSTM model for stock price prediction [J]. Computer Engineering and Applications, 2022, 58(05): 280-286.

[8] Li Chenyang. Research on stock price prediction and quantitative stock selection based on CNN-LSTM [D]. Northwestern University, 2021.

[9] Geng Jingjing, Liu Yumin, Li Yang, Zhao Zhexing. A CNN-LSTM based stock index prediction model [J]. Statistics and Decision Making, 2021, 37(05): 134-138.

[10] Luo X, Zhang JL. Stock price forecasting based on multi-timescale composite deep neural network [J]. Wuhan Finance, 2020, (09): 32-40.