Buying and Selling Decision in the Brazilian Stock Exchange Financial Market by a Neo Fuzzy Neuron (NFN) Applied to the Hurwicz Criterion

• Gabriel S. Rosa CEFET-MG
• Pedro H. Pereira CEFET-MG
• Alisson M. Silva CEFET-MG
• Charlene C. Resende CEFET-MG

DOI: https://doi.org/10.5753/bwaif.2023.230686

Abstract

This work introduces an approach for making decisions on buying and selling stocks in the Brazilian Stock Exchange to maximize profits in each operation. The proposed approach was built using the Neo-Fuzzy-Neuron (NFN) network to predict the future value of stocks and the Hurwicz criterion for decision analysis under risk and uncertainty, considering different degrees of optimism and pessimism. The approach was applied to Petrobras stocks (PETR4), and the results obtained were compared with the ”buy and hold”strategy. The computational results and comparisons suggest that the proposed approach is promising and provides a significant return on investment

References

Amaral, V. L. d. (2021). Sistemas fuzzy evolutivos na previsão e recomendação de investimentos em criptomoedas. Master’s thesis, Centro Federal de Educação Tecnológica de Minas Gerais, Belo Horizonte - MG.

Aminimehr, A., Raoofi, A., Aminimehr, A., and Aminimehr, A. (2022). A comprehensive study of market prediction from efficient market hypothesis up to late intelligent market prediction approaches. Computational Economics, 60(2):781–815.

Anand, C. (2021). Comparison of stock price prediction models using pre-trained neural networks. Journal of Ubiquitous Computing and Communication Technologies (UCCT), 3(02):122–134.

Bekaert, G., Engstrom, E., and Ermolov, A. (2021). Macro risks and the term structure of interest rates. Journal of Financial Economics, 141(2):479–504.

Bloomberg (2017). Petroleo brasileiro.

Bottou, L. et al. (1991). Stochastic gradient learning in neural networks. Proceedings of Neuro-Nımes, 91(8):12.

Carvalho, V. P. d. et al. (2018). Previsão de séries temporais no mercado financeiro de ações com o uso de rede neural artificial.

Debastiani, C. A. (2007). Candlestick: um método para ampliar lucros na Bolsa de Valores. Novatec Editora.

Felizardo, L., Oliveira, R., Del-Moral-Hernandez, E., and Cozman, F. (2019). Comparative study of bitcoin price prediction using wavenets, recurrent neural networks and other machine learning methods. In 2019 6th International Conference on Behavioral, Economic and Socio-Cultural Computing (BESC), pages 1–6. IEEE.

Foxbit (2020). Gráfico de candles: o que é e como interpretar.

Jiang, M., Jia, L., Chen, Z., and Chen, W. (2022). The two-stage machine learning ensemble models for stock price prediction by combining mode decomposition, extreme learning machine and improved harmony search algorithm. Annals of Operations Research, pages 1–33.

Kahneman, D. and Tversky, A. (2013). Prospect theory: An analysis of decision under risk. In Handbook of the fundamentals of financial decision making: Part I, pages 99–127. World Scientific.

Kodama, L. S. (2021). Estudo da rentabilidade de fundos imobiliários com utilização da média móvel.

Mishkin, F. S. and Eakins, S. G. (2015). Financial markets and institutions, eight edition.

Murphy, J. J. (1999). Technical analysis of the financial markets: A comprehensive guide to trading methods and applications. Penguin.

Nametala, C. A., Souza, J. V. d., Pimenta, A., and Carrano, E. G. (2023). Use of econometric predictors and artificial neural networks for the construction of stock market investment bots. Computational Economics, 61(2):743–773.

Ni, J. and Xu, Y. (2021). Forecasting the dynamic correlation of stock indices based on deep learning method. Computational Economics, pages 1–21.

Refenes, A. N. and Azema-Barac, M. (1994). Neural network applications in financial asset management. Neural Computing & Applications, 2:13–39.

Resende, C. C. d. (2021). Modelos matemático-computacional para previsão de tendência de preços: Abordagem com múltiplos ativos buscando oportunidades em desvios da hipótese de mercado eficiente. Master’s thesis, Centro Federal de Educação Tecnológica de Minas Gerais, Belo Horizonte MG.

Ruder, S. (2016). An overview of gradient descent optimization algorithms. arXiv preprint arXiv:1609.04747.

Samuelson, P. A. (2016). Proof that properly anticipated prices fluctuate randomly. In The world scientific handbook of futures markets, pages 25–38. World Scientific.

Sheng, L., Zhu, Y., and Hamalainen, T. (2013). An uncertain optimal control model with hurwicz criterion. Applied Mathematics and Computation, 224:412–421.

Silva, A. M. d. (2014). Sistemas Neuro-Fuzzy Evolutivos: Novos Algoritmos de Aprendizado e Aplicações. PhD thesis, Universidade Federal de Minas Gerais, Escola de Engenharia, Programa de Pós-Graduação em Engenharia Elétrica, Belo Horizonte.

Takagi, T. and Sugeno, M. (1985). Fuzzy identification of systems and its applications to modeling and control. IEEE transactions on systems, man, and cybernetics, (1):116–132.

Tsang, K., Samsatli, N., and Shah, N. (2007). Capacity investment planning for multiple vaccines under uncertainty: 2: Financial risk analysis. Food and Bioproducts Processing, 85(2):129–140.

Wang, Z. (2022). Uncertain differential game with hurwicz criterion. Journal of Ambient Intelligence and Humanized Computing, pages 1–11.

Yamakawa, T. (1992). A neo fuzzy neuron and its applications to system identification and prediction of the system behavior. In Proc. of the 2nd Int. Conf. on Fuzzy Logic & Neural Networks, pages 477–483.

Yilmaz, F. M. and Yildiztepe, E. (2022). Statistical evaluation of deep learning models for stock return forecasting. Computational Economics, pages 1–24.