Welcome to Francis Academic Press

Academic Journal of Computing & Information Science, 2023, 6(10); doi: 10.25236/AJCIS.2023.061004.

Research on analysis and application of quantitative investment strategies based on deep learning

Author(s)

Zhou Senxin, Zhang Sitong, Xie Linna

Corresponding Author:
Zhou Senxin
Affiliation(s)

Anhui University of Finance and Economics, Bengbu, Anhui Province,233000, China

Abstract

Due to the dynamics and complexity of the stock market, stock prediction models may encounter some challenges in predicting future stock movements, resulting in their poor generalisation ability. This paper discusses the application and effectiveness of deep learning technology in the financial field by studying the quantitative investment strategy based on deep learning. First, theoretical foundations of deep learning are introduced. Then, the methods for constructing quantitative investment strategies based on Long Short-Term Memory Network (LSTM) are elaborated, including data preprocessing, model selection and training, and strategy execution. Next, the performance and stability of the strategy are evaluated through backtesting and empirical analysis of historical data. Finally, the research results are summarized, and the direction of further research and application is prospected.

Keywords

Quantitative investment, Deep learning, Strategy analysis, Performance evaluation

Cite This Paper

Zhou Senxin, Zhang Sitong, Xie Linna. Research on analysis and application of quantitative investment strategies based on deep learning. Academic Journal of Computing & Information Science (2023), Vol. 6, Issue 10: 24-30. https://doi.org/10.25236/AJCIS.2023.061004.

References

[1] Sun Ruiqi. Research on US stock index price trend prediction model based on LSTM neural network [D]. Beijing: Capital University of Economics and Business, 2016

[2] Yu Xiaojian,Liu Guopeng,Liu Jianlin et al. Stock index prediction based on LSTM network and text sentiment analysis[J/OL]. China Management Science:1-12[2023-08-26]. DOI:10.16381/j.cnki.issn1003-207x.2021.0084.

[3] PENG Yan, LIU Yuhong,ZHANG Rongfen. Modelling and analysis of stock price prediction based on LSTM[J]. Computer Engineering and Applications, 2019,55(11):209-212.

[4] Md A Q, Kapoor S, AV C J, et al. Novel optimization approach for stock price forecasting using multi-layered sequential LSTM[J]. Applied Soft Computing, 2023, 134: 109830.

[5] Bao Zhenshan,Guo Junnan,Xie Yuan et al. Stock price rise and fall prediction model based on LSTM-GA[J]. Computer Science,2020,47(S1):467-473.

[6] Briola A, Turiel J, Marcaccioli R, et al. Deep reinforcement learning for active high frequency trading[J]. arXiv preprint arXiv:2101.07107, 2021.

[7] Sezer O B, Gudelek M U, Ozbayoglu A M. Financial time series forecasting with deep learning: A systematic literature review: 2005–2019[J]. Applied soft computing, 2020, 90: 106181.

[8] https://github.com/huseinzol05/Stock-Prediction-Models