Hybrid Neural Networks Applied to Brazilian Stock Market
DOI:
https://doi.org/10.22456/2175-2745.88911Keywords:
Artificial Intelligence, Artificial Neural Networks, Genetic Algorithms.Abstract
The stock market is a stochastic, dynamic environment and is in constant evolution, and its prediction represents a big challenge. Many studies presented in the state of the art are facing this challenge, by making use of Artificial Neural Networks (ANN) as a tool to make such prediction. In this paper a comparative study is made with different methods in order to predict the Brazilian stock market through the Bovespa Index. An ANN was developed and its performance was compared against a hybrid model, in which a Genetic Algorithm (GA) is proposed as an alternative to improve the performance of this ANN. The results obtained were an average accuracy of 55.04% and 55.73% respectively, demonstrating that algorithms such as a GA have the capability of improving the performance of ANN for the stock market prediciton.
Downloads
References
NORVIG, P.; RUSSELL, S. Inteligência Artificial: Traducão da 3a Edição. São Paulo: Elsevier Brasil, 2013.
RALEVIC, N. M. et al. The comparative analyses of the nonparametric methods for investment return prediction. In: IEEE. Intelligent Systems and Informatics (SISY), 2015 IEEE 13th International Symposium on. [S.l.], 2015. p. 111–115.
AZEVEDO, F. M. D.; BRASIL, L. M.; OLIVEIRA, R. C. L. de. Redes neurais com aplicações em controle e em sistemas especialistas. Florianopolis: Visual Books, 2000.
KOLAMBE, M. Survey paper on stock market prediction. International Journal of Innovative Research in Computer and communication engineering, v. 4, n. 10, 2016.
SUTKATTI, R.; TORSE, D. Stock market forecasting techniques: A survey. International Research Journal of Engineering and Technology, v. 6, n. 5, 2019.
GREAVES, A.; AU, B. Using the bitcoin transaction graph to predict the price of bitcoin. Quoted, v. 3, p. 22, 2015.
DEVI, B. U.; SUNDAR, D.; ALLI, P. An optimized approach to predict the stock market behavior and investment decision making using benchmark algorithms for naive investors. In: IEEE. Computational Intelligence and Computing Research (ICCIC), 2013 IEEE International Conference on. [S.l.], 2013. p. 1–5.
WU, J.-Y.; LU, C.-J. Computational intelligence approaches for stock price forecasting. In: IEEE. Computer, Consumer and Control (IS3C), 2012 International Symposium on. [S.l.], 2012. p. 52–55.
BOYACIOGLU, M. A.; AVCI, D. An adaptive network-based fuzzy inference system (anfis) for the prediction of stock market return: the case of the istanbul stock exchange. Expert Systems with Applications, v. 37, n. 12, p. 7908–7912, 2010.
DENG, Y. et al. A hierarchical fused fuzzy deep neural network for data classification. IEEE Transactions on Fuzzy Systems, v. 25, n. 4, p. 1006–1012, 2017.
CASTILLO, P. A. et al. G-prop: Global optimization of multilayer perceptrons using gas. Neurocomputing, v. 35, n. 1-4, p. 149–163, 2000.
PROCIANOY, J. L.; CIGERZA, G. C. Ipos in emerging markets: a comparison of brazil, india and china. In: VIII Encontro Brasileiro de Financas. [S.l.: s.n.], 2008.
BOVESPA. Mercado de Capitais. Sao Paulo: Bovespa, 1999.
CORNETT, M.; ADAIR, T.; NOFSINGER, J. Finanças. São Paulo: MCGRAW HILL - ARTMED, 2013.
Comissão de Valores Mobiliários. Portal do Investidor: Ações. 2018. Disponível em: ⟨http://www.portaldoinvestidor. gov.br/menu/Menu Investidor/valores mobiliarios/Acoes/⟩.
CREPALDI, S. A. Curso Básico de Contabilidade. São Paulo: Editora Atlas S.A., 2013.
BM&FBOVESPA. Como investir em ações. 2016a. Disponível em: ⟨http://www.bmfbovespa.com.br/pt br/ como-investir/como-investir-em-acoes/⟩.
BM&FBOVESPA. Indice Bovespa. 2016b. Disponível em: ⟨http://www.bmfbovespa.com.br/pt br/produtos/indices/ indices-amplos/indice-bovespa-ibovespa.htm⟩.
B3. Perfil e Historico. 2017. Disponıvel em: ⟨http://ri.bmfbovespa.com.br/static/ptb/perfil-historico. asp?idioma=ptb⟩.
VISUAL CAPITALIST. The 20 Largest Stock Ex- changes in the World. 2017. Dispon ́ıvel em: ⟨http://www. visualcapitalist.com/20-largest-stock-exchanges-world/⟩.
ERNST&YOUNG. Comparing global stock exchanges. 2012. Dispon ́ıvel em: ⟨https://www.biva.mx/documents/ 30877/866719/Comparing+global+stock+exchanges.pdf/ 8419e06d-5433-8d6b-5034-f94c4cdeaf5e⟩.
CHAVES, D. A. T.; ROCHA, K. C. Analise tecnica e fundamentalista: divergencias, similaridades e complemen-tariedades. Monografia (Especializacao)-Departamento de Administracao da Faculdade de Economia, Administracao e Contabilidade, Universidade de Sao Paulo. Sao Paulo, 2004.
ELDER, A. Como Se Transformar em Um Operador e Investidor de Sucesso. Sa ̃o Paulo: Elsevier, 2007.
STOCKCHARTS. Average Directional Index (ADX). 2018. Disponível em: ⟨https://stockcharts.com/ school/doku.php?id=chart school:technical indicators: average directional index adx⟩.
HAYKIN, S. Redes Neurais - 2ed. Porto Alegre: BOOK- MAN COMPANHIA ED, 2001.
KRIESEL, D. A brief introduction on neural networks. 2007.
PISSARENKO, D. Neural networks for financial time series prediction: Overview over recent research. University of Derby in Austria. Dispon ́ıvel em: ⟨http://citeseer.ist.psu. edu/pissarenko02neural.html⟩.
KUMAR, D. A.; MURUGAN, S. Performance analysis of indian stock market index using neural network time series model. In: IEEE. Pattern Recognition, Informatics and Mo- bile Engineering (PRIME), 2013 International Conference on. [S.l.], 2013. p. 72–78.
DORFFNER, G. Neural networks for time series proces- sing. Neural Network World, v. 6, p. 447–468, 1996.
MITCHELL, M. An introduction to genetic algorithms. Cambridge: MIT press, 1998.
AHMAD, F. et al. A ga-based feature selection and parameter optimization of an ann in diagnosing breast cancer. Pattern Analysis and Applications, v. 18, n. 4, p. 861–870, 2015.
INTHACHOT, M.; BOONJING, V.; INTAKOSUM, S. Artificial neural network and genetic algorithm hybrid intelli- gence for predicting thai stock price index trend. Computational intelligence and neuroscience, v. 2016, 2016.
PU, X.; LIN, Y.; SUN, P. A pruned cooperative co- evolutionary genetic neural network and its application on stock market forecast. In: IEEE. The 26th Chinese Control and Decision Conference (2014 CCDC). [S.l.], 2014. p. 2344– 2349.
Yahoo. Yahoo Finance. 2018. Disponivel em: ⟨https: //finance.yahoo.com/⟩.
JAIN, A.; SRINIVASULU, S. Development of effective and efficient rainfall-runoff models using integration of deterministic, real-coded genetic algorithms and artificial neural network techniques. Water Resources Research, v. 40, n. 4, 2004.
