Predição de tendências em séries financeiras utilizando metaclassificadores

Autores

  • Carlos Alberto Silva de Assis Centro Federal de Educação Tecnológica de Minas Gerais
  • Eduardo Gontijo Carrano Universidade Federal de Minas Gerais
  • Adriano Cesar Machado Pereira Universidade Federal de Minas Gerais

DOI:

https://doi.org/10.11606/1980-5330/ea148159

Palavras-chave:

séries financeiras, inteligência computacional, meta-classificador

Resumo

Neste trabalho foi desenvolvido um metaclassificador baseado em métodos de inteligência computacional para prever tendências em séries temporais financeiras. O kernel do metaclassificador foi baseado na ferramenta (Weka). Sete classificadores foram combinados para realizar a metaclassificação. Testes foram realizados com nove ativos da Bolsa de Valores de São Paulo. Os resultados iniciais foram promissores, com boa acurácia na classificação e ganhos de até 100% do valor de capital inicialmente investido no período de um ano.

Downloads

Os dados de download ainda não estão disponíveis.

Biografia do Autor

  • Carlos Alberto Silva de Assis, Centro Federal de Educação Tecnológica de Minas Gerais

    Doutorado em Modelagem Matemática e Computacional pelo Centro Federal de Educação Tecnológica de Minas Gerais (CEFET-MG), Programa de Pós-Graduação em Modelagem Matemática e Computacional (PPGMMC), Belo Horizonte (MG), Brasil (2019).

  • Eduardo Gontijo Carrano, Universidade Federal de Minas Gerais

    Universidade Federal de Minas Gerais (UFMG), Programa de Pós-Graduação em Engenharia
    Elétrica (PPGEE), Belo Horizonte (MG), Brasil.

  • Adriano Cesar Machado Pereira, Universidade Federal de Minas Gerais

    Professor Adjunto da Universidade Federal de Minas Gerais (UFMG), Programa de Pós-Graduação em Ciência da Computação (PPGCC), Belo Horizonte (MG), Brasil.

Referências

A ERNST (2014), ‘Find the right people, processes and technology to manage record-to-report risks’, Managing Operational Tax Risk .

ADVFN (2010), ‘Entenda o que é o IGPM’. Acesso em: 6 jan. 2019. URL: Disponível em: https://br.advfn.com/indicadores/igpm

AGAPITOS, A., BRABAZON, A. & O’NEILL, M. (2017), ‘Regularised gradient boosting for financial time-series modelling’, Computational Management Science v. 14(n. 3), p. 367–391.

Almeida, C. (2016), ‘Os 10 fatos mais marcantes de 2015’, Disponível em: https://super.abril.com.br/sociedade/os-10-fatos-mais-marcantesde-2015/. Acesso em: 6 jan. 2019.

ANGHEL, M. G. (2013), ‘Technical analysis versus fundamental analysis of securities’, Romanian Statistical Review Supplement v. 61(n. 2), p. 257–262.

ARMAKI, A. G., FALLAH, M. F., ALBORZI, M. & MOHAMMADZADEH, A. (2017), ‘A hybrid meta-learner technique for credit scoring of banks customers’, Int J Res Appl Sci Eng Technol v. 7(n. 5), p. 2073–2082.

ASHBY, W. R. (1960), Design for a brain: the origin of adaptive behavior, 2nd ed., Wiley, New Jersey.

ASSAF NETO, A. (2009), Mercado financeiro, 9. ed. edn, Atlas, São Paulo.

BANZHAF,W., FRANCONE, F. D., KELLER, R. E. & NORDIN, P. (1998), Genetic programming: an introduction on the automatic evolution of computer programs and its applications, Morgan Kaufmann Publishers Inc., San Francisco.

BARAK, S., ARJMAND, A. & ORTOBELLI, S. (2017), ‘Fusion of multiple diverse predictors in stock market’, Inf Fusion v. 36(n. 1), p. 90–102.

BARRYMORE, J. (2017), ‘Como funcionam as tendências do mercado de ações’, Disponível em:

http://empresasefinancas.hsw.uol.com.br/tendencias-mercado-deacoes.htm. Acesso em: 6 fev. 2017.

BAYES, T. (1763), ‘An essay towards solving a problem in the doctrine of chances’, Philos Trans R Soc Lond A v. 53(n. 1), p. 370–418.

BOLSA BRASIL BALCÃO (2017), ‘Site da B3’. Acesso em: 6 fev. 2017. URL: Disponível em: http://www.b3.com.br

BOX, G. E. P. & JENKINS, G. M. (1976), Time series analysis: forecasting and control, 2nd ed. edn, Holden-Day, San Francisco.

BREIMAN, L. (1996), ‘Bagging predictors’, Mach Learn v. 24(n. 2), p. 123–140.

BREIMAN, L. (2001), ‘Random Forests’, Mach Learn v. 45(n. 1), p. 5–32.

BÚSSOLA DO INVESTIDOR (2017), ‘Site do Bússola do Investidor’. Acesso em: 31 jan. 2017.

URL: Disponível em: https://www.bussoladoinvestidor.com.br/

CAFFÉ, M. I. R., PEREZ, P. S. & BARANAUSKAS, J. A. (2012), ‘Evaluation of stacking on biomedical data’, Journal of Health Informatics v. 4(n. 3), p. 67–72.

CAVALCANTE, R. C., BRASILEIRO, R. C., SOUZA, V. L. F., NOBREGA, J. P. & OLIVEIRA, A. L. I. (2016), ‘Computational intelligence and financial markets: a survey and future directions’, Expert Syst Appl v. 55(n. 15), p. 194–211.

COHEN, W. W. (1995), Fast effective rule induction, in ‘In: INTERNATIONAL CONFERENCE ON MACHINE LEARNING, 12’, San Francisco, p. 115–123.

CRUZ, R. M. O., SABOURIN, R., CAVALCANTI, G. D. C. & ING-REN, T. (2015), ‘META-DES: a dynamic ensemble selection framework using metalearning’, Pattern Recognit v. 48(n. 5), p. 1925–1935.

DAVIS, J. & GOADRICH, M. (2006), The relationship between precision recall and ROC curves, in ‘In: INTERNATIONAL CONFERENCE ON MACHINE LEARNING, 23’, New York, pp. p. 233–240.

DE MOURA, F. A. (2006), O uso de redes neurais artificiais na previsão de tendências no mercado de ações, PhD thesis, Dissertação (Mestrado em Engenharia de Produção), Universidade Federal de Pernambuco, Recife, 2006.

DI PERSIO, L. & HONCHAR, O. (2016), ‘Artificial neural networks approach to the forecast of stock market price movements’, International Journal of Economics and Management Systems v. 1(n. 1), p. 158–162.

DIETTERICH, T. G. (2000), Ensemble methods in machine learning, in ‘In: INTERNATIONAL WORKSHOP ON MULTIPLE CLASSIFIER SYSTEMS, 1’, Berlin, pp. p. 1–15.

DRUCKER, H., BURGES, C. J. C., KAUFMAN, L., SMOLA, A. & VAPNIK, V. (1997), Support vector regression machines, in ‘In: ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS, 10’, Cambridge, pp. p. 155–161.

DUARTE, F. A., SATO, R. S. & LORENA, A. C. (2018), Uma Aplicação de meta-aprendizagem no mercado euro/dólar, in ‘In: WORKSHOP OF ARTIFICIAL INTELLIGENCE APPLIED TO FINANCE, WAIAF 2019’, São José dos Campos.

DŽEROSKI, S. & ŽENKO, B. (2004), ‘Is combining classifiers with stacking better than selecting the best one?’, Mach Learn v. 54(n. 3), p. 255–273.

ELEVEN FINANCIAL (2017), ‘O que é taxa CDI e como ela funciona?’, Disponível em: https://elevenfinancial.com/o-que-e-taxa-cdi-e-como-elafunciona. Acesso em: 6 jan. 2019.

FREUND, Y. (1999), An adaptive version of the boost by majority algorithm, in ‘In: ANNUAL CONFERENCE ON COMPUTATIONAL LEARNING THEORY, 12’, Santa Cruz, pp. p. 102–113.

GIACOMEL, F., GALANTE, R. & PEREIRA, A. (2015), An algorithmic trading agent based on a neural network ensemble: a case of study in North American and Brazilian stock markets, in ‘In: INTERNATIONAL CONFERENCE ON WEB INTELLIGENCE AND INTELLIGENT AGENT TECHNOLOGY, 2015’, Singapore, pp. p. 230–233.

GISLASON, P. O., BENEDIKTSSON, J. A. & SVEINSSON, J. R. (2006), ‘Random forests for land cover classification’, Pattern Recognit Lett v. 27(n. 4), p. 294–300.

GOLDBERG, D. E. (1989), Genetic algorithms in search, optimization and machine learning, 1st ed. edn, Addison-Wesley Longman Publishing Co., Inc., New York.

HAND, D. J. & YU, K. (2001), ‘Idiots Bayes not so stupid after all?’, Int Stat Rev v. 69(n. 3), p. 385–398.

HEBB, D. O. (1949), The organization of behavior: a neuropsychological theory, Psychology Press, New York.

HO, T. K. (2001), Multiple classifier combination: lessons and next steps, Vol. v. 47 of Series in machine perception and artificial intelligence, World Scientific, chapter c. 7, pp. p. 171–198.

HOLLAND, J. H. (1975), Adaptation in natural and artificial systems, University of Michigan Press, Ann Arbor.

KAMPOURIDIS, M. & OTERO, F. E. B. (2015), ‘Heuristic procedures for improving the predictability of a genetic programming financial forecasting algorithm’, Soft comput v. 21(n. 1), p. 295–310.

KITCHENHAM, B. (2004), Procedures for performing systematic reviews, Technical report, Keele University and NICTA.

KOZA, J. R. (1992), Genetic programming: on the programming of computers by means of natural selection, MIT Press, Cambridge.

KUNCHEVA, L. I. (2004), Combining pattern classifiers: methods and algorithms, 2nd ed. edn, JohnWiley & Sons, Inc., Hoboken.

MC CULLOCH, W. S. & PITTS, W. (1943), ‘A logical calculus of the ideas immanent in nervous activity’, Bull Math Biol v. 5(n. 4), p. 115–133.

METATRADER (2017), ‘Plataforma de NegociaçãoMetaTrader 5’. Acesso em: 6 fev. 2017.

URL: Disponível em: https://www.metatrader5.com/

MYSKOVA, R., HAJEK, P. & OLEJ, V. (2018), ‘Predicting abnormal stock return volatility using textual analysis of news a meta-learning approach’, Amfiteatru Economic v. 20(n. 47), p. 185–201.

NAMETALA, C. A. L., PIMENTA, A., PEREIRA, A. C. M. & CARRANO, E. G. (2016), An automated investment strategy using artificial neural networks and econometric predictors, in ‘In: BRAZILIAN SYMPOSIUM ON INFORMATION, XII, SYSTEMS ON BRAZILIAN SYMPOSIUM ON INFORMATION SYSTEM, 2016’, Vol. v. 1, Porto Alegre, pp. p. 152–159.

NEAPOLITAN, R. E. (2003), Learning bayesian networks, Prentice-Hall, Inc., Upper Saddle River.

NORONHA, M. (2003), Análise técnica: teorias ferramentas estratégias, 5. ed., Editec, Rio de Janeiro.

PATEL, J., SHAH, S., THAKKAR, P. & KOTECHA, K. (2015), ‘Predicting stockmarket index using fusion ofmachine learning techniques’, Expert Syst Appl v. 42(n. 4), p. 2162–2172.

PEARL, J. (1988), Probabilistic reasoning in intelligent systems: networks of plausible inference, Morgan Kaufmann Publishers Inc., San Francisco.

PIMENTA, A., GUIMARÃES, F. G., CARRANO, E. G., NAMETALA, C. A. L. & TAKAHASHI, R. H. C. (2014), Gold miner: a genetic programming based algorithm applied to Brazilian stock market, in ‘In: SYMPOSIUM ON COMPUTATIONAL INTELLIGENCE AND DATAMINING, 2014’, Orlando, p. 397–402.

PLATT, J. C. (1998), Fast training of support vector machines using sequential minimal optimization, in ‘Advances in Kernel methods - support vector learning’, In: Schoelkopf B., Burges C.J.C., Smola, A.J. (eds.), MIT Press, Cambridge.

QUINLAN, J. R. (1993), C4.5: programs for machine learning, 5th ed., Morgan Kaufmann Publishers Inc., San Francisco.

RAMOS, J. P. S. (2003), ‘Fruit sorting using artificial neural networks: bidimensional case’, Ciênc Agrotec v. 27(n. 2), p. 356–362.

ROSENBLATT, F. (1958), ‘The perceptron: a probabilistic model for information storage and organization in the brain’, Psychol Rev v. 65(n. 6), p. 386–408.

SCHAPIRE, R. E. (1990), ‘The strength of weak learnability’, Mach Learn v. 5(n. 2), p. 197–227.

SEEWALD, A. K. (2002), How to make stacking better and faster while also taking care of an unknown weakness, in ‘In: INTERNATIONAL CONFERENCE ON MACHINE LEARNING, 19’, San Francisco, pp. p. 554–561.

SEKER, S. E., MERT, C., AL NAAMI, K., AYAN, U. & öZALP, N. (2013), Ensemble classification over stock market time series and economy news, In: INTERNATIONAL CONFERENCE ON INTELLIGENCE AND SECURITY INFORMATICS, 2013’, Seattle, pp. p. 272–273.

STROUSTRUP, B. (2000), The C++ programming language, 3rd ed., Addison-Wesley Longman Publishing Co., Inc., Boston.

STUDENT (1908), ‘The probable error of a mean’, Biometrika v. 6(n. 1), p. 1–25.

TAN, A. C. & GILBERT, D. (2003), ‘Ensemble machine learning on gene expression data for cancer classification’, Appl Bioinformatics v. 2(n. 3), p. 75–83.

THORSTENSEN, V. H. (1976), A teoria da eficiência no mercado de capitais. Uma revisão da literatura e dos trabalhos empíricos. O modelo de Random walk aplicado ao índice de mercado de ações Bovespa, PhD thesis, Dissertação (Mestre em Administração de Empresas), Escola de Administração de Empresas de São Paulo, Fundação Getúlio Vargas, São Paulo, 1976.

TKÁČ,M. & VERNER, R. (2016), ‘Artificial neural networks in business: two decades of research’, Appl Soft Comput v. 38(n. 1), p. 788–804.

TSAY, R. S. (2005), Analysis of financial time series, 2nd ed. edn, JohnWiley & Sons, Inc., Hoboken.

VAPNIK, V. N. (1995), The nature of statistical learning theory, 1st ed. edn, Springer-Verlag New York, Inc., New York.

VAPNIK, V. N. & CHERVONENKIS, A. Y. (1971), ‘On the uniform convergence of relative frequencies of events to their probabilities’, Theory Probab Appl v. 16(n. 2), p. 264–280.

VARGA, G. (2001), ‘Índice de sharpe e outros indicadores de performance aplicados a fundos de ações brasileiros’, Revista de Administração Contemporânea v. 5(n. 3), p. 215–245.

WERBOS, P. J. (1994), The roots of backpropagation: from ordered derivatives to neural networks and political forecasting, 1st ed. edn, John Wiley & Sons, Inc., Hoboken.

WIDROW, B. & HOFF, M. E. (1960), Adaptive switching circuits, in ‘In: IRE WESCON CONVENTION RECORD, PART 4’, New York, p. 96–104.

WIDROW, B. & HOFF, M. E. (1962), Associative storage and retrieval of digital information in networks of adaptive “neurons”, Springer, Boston, p. 160–160.

WITTEN, I. H. & FRANK, E. (2005), Data mining: practical machine learning tools and techniques, 2nd ed. edn, Morgan Kaufmann Publishers Inc., San Francisco.

WITTEN, I. H., FRANK, E., TRIGG, L., HALL, M., HOLMES, G. & CUNNINGHAM, S. J. (1999), ‘Weka: practical machine learning tools and techniques with java implementations’.

WOLPERT, D. H. (1992), ‘Stacked generalization’, Neural Netw v. 5(n. 2), p. 241–259.

ZHANG, M. & ZHOU, Z. (2014), ‘A review on multi-label learning algorithms’, IEEE Trans Knowl Data Eng v. 26(n. 8), p. 1819–1837.

Downloads

Publicado

2020-03-01

Edição

Seção

Artigos

Como Citar

Assis, C. A. S. de, Carrano, E. G., & Pereira, A. C. M. (2020). Predição de tendências em séries financeiras utilizando metaclassificadores. Economia Aplicada, 24(1), 29-78. https://doi.org/10.11606/1980-5330/ea148159