Abstract
This paper presents the development process of a LSTM prophet which predicts stock market prices, based on historical data and machine learning to identify trends. Predicting prices in the stock market is a challenging task, surrounded by possible turbulent events that impact the final result. In this scenario, for the method proposed here, it is presented (i) the steps to obtain and process the used data for the applied LSTM network; (ii) the motivations for this implementation; (iii) the details regarding methodology and architecture; (iv) the neural architecture search technique used to determine the hyperparameters by tuning them through the iRace algorithm, which is responsible for structuring the network topology in a robust way; and (v) a discussion about quality measures used to compare network settings. Computational experiments in order to analyze the developed tool considered stock tickers from USA and Brazilian financial markets, in addition to the foreign exchange market involving BRL–USD. The obtained results were satisfactory in general, which achieved a high model accuracy, in relation to price tendency, and a low mean absolute percentage error, according to price values, with the analyzed test dataset.
Supported by organization the Brazilian agencies CAPES, CNPq and FAPEMIG.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Althelaya, K.A., El-Alfy, E.S.M., Mohammed, S.: Evaluation of bidirectional LSTM for short-and long-term stock market prediction. In: 9th International Conference on Information and Communication Systems (ICICS), pp. 151–156. IEEE (2018)
Baek, Y., Kim, H.Y.: ModAugNet: a new forecasting framework for stock market index value with an overfitting prevention LSTM module and a prediction LSTM module. Expert Syst. Appl. 113, 457–480 (2018)
Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473 (2014)
Cramer, S., Kampouridis, M., Freitas, A.A., Alexandridis, A.K.: An extensive evaluation of seven machine learning methods for rainfall prediction in weather derivatives. Expert Syst. Appl. 85, 169–181 (2017)
Deb, K., Mohan, M., Mishra, S.: Evaluating the varepsilon-domination based multi objective evolutionary algorithm for a quick computation of pareto-optimal solutions. Evol. Comput. J. 13(4), 501–525 (2005)
Deb, K., Pratap, A., Agarwal, S., Meyarivan, T.: A fast and elitist multi objective genetic algorithm: NSGA-ii. IEEE Trans. Evol. Comput. 6(2), 182–197 (2002)
Edwards, R.D., Magee, J., Bassetti, W.C.: Technical Analysis of Stock Trends. CRC Press (2018)
Fama, E.F.: Efficient capital markets: a review of theory and empirical work. J. Finance 25(2), 383–417 (1970). http://www.jstor.org/stable/2325486
Gandhmal, D.P., Kumar, K.: Systematic analysis and review of stock market prediction techniques. Comput. Sci. Rev. 34, 100190 (2019)
Giacomel, F.d.S.: Um método algorítmico para operações na bolsa de valores baseado em ensembles de redes neurais para modelar e prever os movimentos dos mercados de ações. Tese de mestrado, UFRGS (2016)
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)
Jin, Z., Yang, Y., Liu, Y.: Stock closing price prediction based on sentiment analysis and LSTM. Neural Comput. Appl. 32(13), 9713–9729 (2020)
Kampouridis, M., Otero, F.E.: Evolving trading strategies using directional changes. Expert Syst. Appl. 73, 145–160 (2017)
Kissell, R.: Algorithmic Trading Methods: Applications Using Advanced Statistics, Optimization, and Machine Learning Techniques. Academic Press (2021)
Liu, S., Liao, G., Ding, Y.: Stock transaction prediction modeling and analysis based on LSTM. In: 2018 13th IEEE Conference on Industrial Electronics and Applications (ICIEA), pp. 2787–2790. IEEE (2018)
López-Ibáñez, M., Dubois-Lacoste, J., Cáceres, L.P., Birattari, M., Stützle, T.: The irace package: iterated racing for automatic algorithm configuration. Oper. Res. Perspect. 3, 43–58 (2016)
Malkiel, B.G.: A random walk down wall street. w. w (1973)
Mohamed, I., Otero, F.E.: A multi objective optimization approach for market timing. In: Proceedings of the 2020 Genetic and Evolutionary Computation Conference, pp. 22–30 (2020)
Nakagawa, S., Schielzeth, H.: A general and simple method for obtaining R2 from generalized linear mixed-effects models. Methods Ecol. Evol. 4(2), 133–142 (2013)
Nelson, D.M., Pereira, A.C., de Oliveira, R.A.: Stock market’s price movement prediction with LSTM neural networks. In: 2017 International Joint Conference on Neural Networks (IJCNN), pp. 1419–1426. IEEE (2017)
Palepu, K.G., Healy, P.M., Wright, S., Bradbury, M., Coulton, J.: Business Analysis and Valuation: Using Financial Statements. Cengage AU (2020)
Rondel, G., Hilkner, R.: Técnicas de redes neurais para análise e previsão do mercado de ações. Relatório de Graduação, Projeto Final, UNICAMP (2019)
Sahni, R.: Analysis of stock market behaviour by applying chaos theory. In: 2018 9th International Conference on Computing, Communication and Networking Technologies (ICCCNT), pp. 1–4. IEEE (2018)
Shah, D., Isah, H., Zulkernine, F.: Stock market analysis: a review and taxonomy of prediction techniques. Int. J. Financ. Stud. 7(2), 26 (2019)
Woodruff, M., Herman, J.: pareto.py: a varepsilon-non-domination sorting routine (2013). https://github.com/matthewjwoodruff/pareto.py
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Costa, T.F., da Cruz, A.R. (2022). Stock-Pred: The LSTM Prophet of the Stock Market. In: Pereira, A.I., Košir, A., Fernandes, F.P., Pacheco, M.F., Teixeira, J.P., Lopes, R.P. (eds) Optimization, Learning Algorithms and Applications. OL2A 2022. Communications in Computer and Information Science, vol 1754. Springer, Cham. https://doi.org/10.1007/978-3-031-23236-7_21
Download citation
DOI: https://doi.org/10.1007/978-3-031-23236-7_21
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-23235-0
Online ISBN: 978-3-031-23236-7
eBook Packages: Computer ScienceComputer Science (R0)