Abstract
The paper proposes and compares two models for creating a recommendation system in the stock market, based on convolutional neural networks (CNN). The first model encodes the values of the time series of the stock exchange quotations into multiple technical indicators incorporating them in the form of an image. These indicators are defined on the closing prices of the stock quotes from the previous day The second model introduces some modifications of the previous approach by changing the definitions of the technical indicators. The numerical experiments have shown its improved performance. Both models are generated from the one-dimensional stock market data and saved as images. The CNN neural network uses these images in the training and testing phases. The numerical experiments aimed at maximizing profit from the investments have been performed on the stock data of the six largest companies listed on the Warsaw Stock Exchange. The recommendations for companies were classified in the form of three classes (Buy, Sell, Hold). The numerical results for the proposed methods are presented and compared with other investment methods typically used in the stock market.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Li, X., Kang, Y., Li, F.: Forecasting with time series imaging. arXiv:1904.08064 (2020). doi.org/10.48550/arXiv:1904.08064
Sezer, O., Ozbayoglu, M.: Algorithmic financial trading with deep convolutional neural networks: time series to image conversion approach. Appl. Soft Comput. 70, 525–538 (2018). https://doi.org/10.1016/j.asoc.2018.04.024
Fischer, T., Krauss, C.: Deep learning with long short-term memory networks for financial market predictions. Eur. J. Oper. Res. 259(2), 689–702 (2017). https://doi.org/10.1016/j.ejor.2017.11.054
Moghar, A., Hamiche, M.: Stock market prediction using LSTM recurrent neural network. Procedia Comput. Sci. 170, 1168–1173 (2020). https://doi.org/10.1016/j.procs.2020.03.049
Osowski, S.: Prediction of air pollution using LSTM. In: International Work-Conference on Artificial Neural Networks, Madera (2021). https://doi.org/10.1007/978-3-030-85099-917
Chen, J.F., Chen, W.L., Huang, C.P., Huang, S.H., Chen, A.P.: Financial time-series data analysis using deep convolutional neural networks. In: 7th International Conference on Cloud Computing and Big Data (CCBD), IEEE (2016). https://doi.org/10.1109/CCBD.2016.027
Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press (2016)
Canziani, A., Paszke, A., Culurciello, E.: An analysis of deep neural network models for practical applications. arXiv:1605.07678 (2016). https://doi.org/10.48550/arXiv.1605.07678
Kingma, D.P., Ba, J.L.: Adam, a method for stochastic optimization, arXiv:1412.6980v0 (2014). https://doi.org/10.48550/arXiv.1412.6980
B. Shannon, Technical analysis using multiple timeframes, LifeVest, Colorado, USA (2008)
Murphy, J.J.: Technical analysis of the financial markets: a comprehensive guide to trading methods and applications, Penguin Group (USA) Inc. (1999)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Parzyszek, M., Osowski, S. (2023). Deep Learning Recommendation System for Stock Market Investments. In: Rojas, I., Joya, G., Catala, A. (eds) Advances in Computational Intelligence. IWANN 2023. Lecture Notes in Computer Science, vol 14134. Springer, Cham. https://doi.org/10.1007/978-3-031-43085-5_21
Download citation
DOI: https://doi.org/10.1007/978-3-031-43085-5_21
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-43084-8
Online ISBN: 978-3-031-43085-5
eBook Packages: Computer ScienceComputer Science (R0)