Deep architectures for long-term stock price prediction with a heuristic-based strategy for trading simulations


Autoři: Catalin Stoean aff001;  Wiesław Paja aff003;  Ruxandra Stoean aff001;  Adrian Sandita aff004
Působiště autorů: Romanian Institute of Science and Technology, Cluj-Napoca, Romania aff001;  Grupo Ingeniería de Sistemas Integrados (TIC-125), E.T.S.I. Telecomunicación, Universidad de Malaga, Malaga, Spain aff002;  Faculty of Mathematics and Natural Sciences, University of Rzeszów, Rzeszów, Poland aff003;  Faculty of Sciences, University of Craiova, Craiova, Romania aff004
Vyšlo v časopise: PLoS ONE 14(10)
Kategorie: Research Article
prolekare.web.journal.doi_sk: 10.1371/journal.pone.0223593

Souhrn

Stock price prediction is a popular yet challenging task and deep learning provides the means to conduct the mining for the different patterns that trigger its dynamic movement. In this paper, the task is to predict the close price for 25 companies enlisted at the Bucharest Stock Exchange, from a novel data set introduced herein. Towards this scope, two traditional deep learning architectures are designed in comparison: a long short-memory network and a temporal convolutional neural model. Based on their predictions, a trading strategy, whose decision to buy or sell depends on two different thresholds, is proposed. A hill climbing approach selects the optimal values for these parameters. The prediction of the two deep learning representatives used in the subsequent trading strategy leads to distinct facets of gain.

Klíčová slova:

Climbing – Convolution – Deep learning – Machine learning – Neural networks – Simulation and modeling – Stock markets – Romanian people


Zdroje

1. Gehring J, Auli M, Grangier D, Yarats D, Dauphin YN. Convolutional Sequence to Sequence Learning. CoRR. 2017;abs/1705.03122.

2. Kim T, Kim HY. Forecasting stock prices with a feature fusion LSTM-CNN model using different representations of the same data. PLOS ONE. 2019;14(2):1–23. doi: 10.1371/journal.pone.0212320

3. Arévalo A, Niño J, Hernández G, Sandoval J. High-Frequency Trading Strategy Based on Deep Neural Networks. In: Huang DS, Han K, Hussain A, editors. Intelligent Computing Methodologies. Cham: Springer International Publishing; 2016. p. 424–436.

4. Chong E, Han C, Park FC. Deep learning networks for stock market analysis and prediction: Methodology, data representations, and case studies. Expert Systems with Applications. 2017;83:187—205. https://doi.org/10.1016/j.eswa.2017.04.030

5. Nelson DMQ, Pereira ACM, de Oliveira RA. Stock market’s price movement prediction with LSTM neural networks. In: 2017 International Joint Conference on Neural Networks (IJCNN); 2017. p. 1419–1426.

6. Bao W, Yue J, Rao Y. A deep learning framework for financial time series using stacked autoencoders and long-short term memory. PLOS ONE. 2017;12(7):1–24. doi: 10.1371/journal.pone.0180944

7. Zhang L, Aggarwal C, Qi GJ. Stock Price Prediction via Discovering Multi-Frequency Trading Patterns. In: Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. KDD’17. New York, NY, USA: ACM; 2017. p. 2141–2149. Available from: http://doi.acm.org/10.1145/3097983.3098117.

8. Singh R, Srivastava S. Stock Prediction Using Deep Learning. Multimedia Tools Appl. 2017;76(18):18569–18584. doi: 10.1007/s11042-016-4159-7

9. Olah C. Understanding LSTM Networks; 2015. Available from: http://colah.github.io/posts/2015-08-Understanding-LSTMs/.

10. Srivastava N, Hinton G, Krizhevsky A, Sutskever I, Salakhutdinov R. Dropout: A Simple Way to Prevent Neural Networks from Overfitting. J Mach Learn Res. 2014;15(1):1929–1958.

11. Lin L, Cao L, Wang J, Zhang C. Zhang C. The applications of genetic algorithms in stock market data mining optimization. In: In: Zanasi A, Ebecken NFF, Brebbia CA, editors. Data mining V. WIT Press; 2004. p. 448–455.

12. Kroha P, Friedrich M. Comparison of Genetic Algorithms for Trading Strategies. In: Geffert V, Preneel B, Rovan B, Štuller J, Tjoa AM, editors. SOFSEM 2014: Theory and Practice of Computer Science. Cham: Springer International Publishing; 2014. p. 383–394.

13. Stoean R. Analysis on the potential of an EA-surrogate modelling tandem for deep learning parametrization: an example for cancer classification from medical images. Neural Computing and Applications. 2018;. doi: 10.1007/s00521-018-3709-5

14. Lichtblau D, Stoean C. Cancer diagnosis through a tandem of classifiers for digitized histopathological slides. PLOS ONE. 2019;14(1):1–20. doi: 10.1371/journal.pone.0209274

15. Henrique BM, Sobreiro VA, Kimura H. Stock price prediction using support vector regression on daily and up to the minute prices. The Journal of Finance and Data Science. 2018;4(3):183—201. https://doi.org/10.1016/j.jfds.2018.04.003

16. Basak S, Kar S, Saha S, Khaidem L, Dey SR. Predicting the direction of stock market prices using tree-based classifiers. The North American Journal of Economics and Finance. 2019;47:552–567. https://doi.org/10.1016/j.najef.2018.06.013

17. Preuss M, Stoean C, Stoean R. Niching foundations: basin identification on fixed-property generated landscapes. In: Krasnogor N, Lanzi PL, editors. 13th Annual Conference on Genetic and Evolutionary Computation (GECCO-2011). ACM; 2011. p. 837–844.

18. Stoean C, Stoean R. Evolution of Cooperating Classification Rules with an Archiving Strategy to Underpin Collaboration. In: Intelligent Systems and Technologies: Methods and Applications. Berlin, Heidelberg: Springer Berlin Heidelberg; 2009. p. 47–65. Available from: https://doi.org/10.1007/978-3-642-01885-5_3.

19. Nam K, Seong N. Financial news-based stock movement prediction using causality analysis of influence in the Korean stock market. Decision Support Systems. 2019;117:100—112. https://doi.org/10.1016/j.dss.2018.11.004


Článok vyšiel v časopise

PLOS One


2019 Číslo 10