Redes neuronales para predecir el comportamiento del conjunto de activos financieros más líquidos del mercado de valores peruano

  • B Bellido Universidad de Lima
Palabras clave: Activo financiero, Fondo cotizado, redes neuronales, rendimiento bursátil, riesgo bursátil

Resumen

La presente investigación tiene como propósito identificar una herramienta de inteligencia artificial basada en redes neuronales para predecir el comportamiento de rendimiento y riesgo del conjunto de activos financieros basados en acciones que reflejen con mayor exactitud el movimiento bursátil del mercado de valores peruano. La investigación identificó inicialmente el activo financiero más apropiado para estimar los valores de rendimiento y riesgo de la cartera de acciones 50% más liquida del mercado peruano en el período 2010-2016. A partir del activo seleccionado se utilizó la técnica de redes neuronales artificiales con un perceptrón multicapa con regresión configurado con 3 capas (21,85,2) usando una función de activación logística con un optimizador LBFGS a una taza de aprendizaje de 0.01 para establecer los patrones financieros, operacionales, comerciales o de gobierno corporativo que puedan explicar y/o predecir el comportamiento del mismo en el mercado. La investigación concluye que la capacidad de generación de caja y la velocidad con la que se rotan los activos, así como la velocidad con la que se desembolsa el Capex constituyen los principales factores que influencian en la determinación de las mejores combinaciones de rendimiento y riesgo para el grupo de activos financieros considerados como materia de estudio, independiente del sector de mercado en el cual se opera. La investigación encontró una red neuronal capaz de aproximar la predicción de rendimiento y riesgo con un 76.93% de eficacia para el conjunto de activos seleccionados en el periodo de estudio. La investigación aporta un reconocimiento de patrones diferenciados en aspectos financieros, operacionales, comerciales y de gobierno corporativo con un especial énfasis en la capacidad gerencial que los genera cuya influencia se refleja en el desempeño del conjunto de activos estudiados por medio de la técnica de redes neuronales generando una herramienta predictiva para estimar su comportamiento bursátil.

Citas

Abdou, K., & Nasereddin, M. (2011). The persistence of hedge fund strategies in different economic periods: A support vector machine approach.Journal of Derivatives & Hedge Funds ,17(1), 2-15. doi: 10.1057/jdhf.2011.1.

Akhter, M. R. (2014). A hybrid intelligent method of predicting stock returns. Advances in Artificial Neural Systems ,doi: 10.1155/2014/246487.

Arugaslan, O., & Samant, A. (2014). Evaluating S&P 500 sector ETFs using risk-adjusted performance measures.Journal of Finance, Accounting and Management ,5(1), 48-62.

Bello, Z. (2012). The investment performance and tracking errors of small-cap ETFs.Global Journal of Finance and Banking Issues ,6(6), 12-20. [ Links ]

Bello, Z. Y. (2012). The relative performance of equity index ETFs and equity index mutual funds.European Journal of Finance and Banking Research ,5(5), 35-46. [ Links ]

Bonnans, J.; Gilbert, J.; Lemaréchal, C.; Sagastizábal, C. (2006), Numerical optimization: Theoretical and practical aspects, Universitext (Second revised ed. of translation of 1997 French ed.), Berlin: Springer-Verlag, pp. xiv+490, doi:10.1007/978-3-540-35447-5, ISBN 3-540-35445-X, MR 2265882 French Original: Optimisation numérique: Aspects théoriques et pratiques ISBN 3-540-63183-6.

Borkovec, M., & Serbin, V. (2013). Create or buy: A comparative analysis of liquidity and transaction costs for selected U.S. ETFs.Journal of Portfolio Management ,39(4), 118-131,12. [ Links ]

Broyden, C.(1970), "The convergence of a class of double-rank minimization algorithms", Journal of the Institute of Mathematics and Its Applications, 6: 76-90, doi:10.1093/imamat/6.1.76 [ Links ]

Chang, C. E., Krueger, T. M., & Witte, H. D. (2015). Do ETFs outperform CEFs in fixed income investing?American Journal of Business ,30(4), 231-246. [ Links ]

Charumathi, B., & Suraj, E. S. (2014). Refining ohlson model for valuing bank stocks- an artificial neural network approach.Independent Business Review ,7(2), 32-48.

Chien-Feng, H., Chi-Jen Hsu, Chi-Chung, C., Bao, R. C., & Chen-An, L. (2015). An intelligent model for pairs trading using genetic algorithms.Computational Intelligence and Neuroscience: CIN ,doi: 10.1155/2015/939606

Chen, H., Shin, S. H., & Sun, X. (2015). Return-enhancing strategies with international ETFs: Exploiting the turn-of-the-month effect.Financial Services Review ,24(3), 271-288.

Chung, D. Y., & Hrazdil, K. (2013). Speed of convergence to market efficiency in the ETFs market.Managerial Finance ,39(5), 457-475. doi: 10.1108/03074351311313852

DiLellio, J. A., & Jakob, K. (2011). ETF trading strategies to enhance client wealth maximization.Financial Services Review ,20(2), 145-163.

DiLellio, J. A., Hesse, R., & Stanley, D. J. (2014). Portfolio performance with inverse and leveraged ETFs.Financial Services Review ,23(2), 123-149.

Dunham, L. M., Jorgensen, R., & Washer, K. (2016). Securities lending activities in mutual funds and ETFs: Ethical considerations.Journal of Business Ethics ,139(1), 21-28. doi: 10.1007/s10551-015-2609-1

Dunham, L. M., & Simpson, T. H. (2015). An analysis of the impact of securities lending on the performance of ETFs.The Journal of Wealth Management , 17(4), 75-84,6.

Ebadati, O. M. E., & Mortazavi, M. T. (2018). An efficient hybrid machine learning method for time series stock market forecasting. Neural Network World , 28(1), 41-55. doi: 10.14311/NNW.2018.28.003

Fama, E. 1970. "Efficient Capital Markets: A Review of Theory and Empirical Work", The Journal of Finance, v. 25, 383-417.

Fletcher, R. (1987), Practical methods of optimization (2nd ed.), New York: John Wiley & Sons, ISBN 978-0-471-91547-8 [ Links ]

Garson, D.(1991) Interpreting neural-network connection weights. AI Expert, 6(4):46-51, 1991. [ Links ]

Giesecke M. & Contreras C. (2007). Bolsa de Valores de Lima 150 años de Historia. BVL 1ra. Edición dic 2007, Peru

Goldfarb, D. (1970), "A Family of Variable Metric Updates Derived by Variational Means", Mathematics of Computation, 24 (109): 23-26, doi:10.1090/S0025-5718-1970-0258249-6

Hansen, L. (2002). "Method of Moments". In Smelser, N. J.; Bates, P. B. International Encyclopedia of the Social and Behavior Sciences. Oxford: Pergamon.

Hamid, S. A., & Habib, A. (2014). Financial forecasting with neural networks.Academy of Accounting and Financial Studies Journal ,18(4), 37-55.

Hegazy, O., Soliman, O. S., & Salam, M. A. (2015). Comparative study between FPA, BA, MCS, ABC, and PSO algorithms in training and optimizing of LS-SVM for stock market prediction.International Journal of Advanced Computer Research ,5(18), 35-45.

Henderson, B. J., & Buetow, G. W. (2014). Are flows costly to ETF investors? Journal of Portfolio Management ,40(3), 100-112,10.

Huang, C., Chiou, C., Wu, T., & Yang, S. (2015). An integrated DEA-MODM methodology for portfolio optimization.Operational Research ,15(1), 115-136. doi: 10.1007/s12351-014-0164-7

Ivanov, S. I. (2011). ETF volatility around the New York stock exchange close. Journal of Accounting and Finance ,11(4), 37-46.

Ivanov, S. I. (2013). High-frequency analysis of exchange traded funds' pricing deviation.Managerial Finance ,39(5), 509-524. doi: 10.1108/03074351311313834

Ivanov, S. I. (2015). Intraday analysis of currency ETFs.International Journal of Managerial Finance , 11(4), 438-450.

Ivanov, S. I. (2016). Analysis of the factors impacting ETFs net fund flow changes.Studies in Economics and Finance ,33(2), 244-261.

Jacobsen, B. (2015). The big ETF charade.Journal of Portfolio Management ,41(2), 3-4.

Jung-Chu, L. (2017). Does pricing deviation of exchange-traded funds predict ETF returns?Asian Economic and Financial Review ,7(8), 748-759. doi: 10.18488/journal.aefr.2017.78.748.759.

Karceski, J. (2002). Returns-chasing behavior, mutual funds, and beta's death. Journal of Financial and Quantitative Analysis ,37(4), 559-594.

Kanuri, S. (2016). Hedged ETFs: Do they add value?Financial Services Review ,25(2), 181-198.

Koti, R. T. (2013). Analysis of exchange traded funds & mutual funds.I-Manager's Journal on Management ,7(3), 12-25.

Li, M., Klein, D., & Zhao, X. (2012). Empirical analysis of ETF intraday trading. Financial Services Review ,21(2), 149-176.

Lin, J. (2013). Volume-return relationship in ETF markets: A reexamination of the costly short-sale hypothesis.Journal of Applied Finance and Banking ,3(6), 201-224.

Lu, L., Wang, J., & Zhang, G. (2012). Long term performance of leveraged ETFs. Financial Services Review ,21(1), 63-80.

Luenberger, D.; Ye, Y.(2008), Linear and nonlinear programming, International Series in Operations Research & Management Science, 116 (Third ed.), New York: Springer, pp. xiv+546, ISBN 978-0-387-74502-2, MR 2423726

Madhavan, V. (2014). Investigating the nature of nonlinearity in indian exchange traded funds (ETFs).Managerial Finance ,40(4), 395-415. doi: 10.1108/MF-07-2013-0170

Milonas, N. T., & Rompotis, G. G. (2013). Does intervalling effect affect ETFs? Managerial Finance ,39(9), 863-882. doi: 10.1108/MF-01-2010-0004

Milonas, N. T., & Rompotis, G. G. (2015). The performance of German fixed-income ETFs: In the presence of the debt crisis.Aestimatio ,(11), 46-77. doi: 10.5605/IEB.11.2

Meric, I., Gishlick, H. E., Taga, L. S., & Meric, G. (2011). Risks, returns, and portfolio diversification benefits of country index funds in bear and bull markets.Business and Economics Research Journal ,2(1), 1-14.

Myšková, R., Hájek, P., & Olej, V. (2018). Predicting abnormal stock return volatility using textual analysis of news - a meta-learning approach.Amfiteatru Economic ,20(47), 185-201.

Narend, S., & Thenmozhi, M. (2016). What drives fund flows to index ETFs and mutual funds? A panel analysis of funds in India.Decision ,43(1), 17-30. doi: 10.1007/s40622-016-0124-6

Nocedal, J.; Wright, S.(2006), Numerical Optimization (2nd ed.), Berlin, New York: Springer -Verlag, ISBN 978-0-387-30303-1

Osterhoff, F., & Kaserer, C. (2016). Determinants of tracking error in German ETFs - the role of market liquidity.Managerial Finance ,42(5), 417-437.

Papadelis, S., Flamos, A., & Androulaki, S. (2012). Setting the framework for a business strategy assessment model.International Journal of Energy Sector Management ,6(4), 488-517. 10.1108/17506221211281993

Qiu, M., & Song, Y. (2016). Predicting the direction of stock market index movement using an optimized artificial neural network model.PLoS One ,11(5) doi: 10.1371/journal.pone.0155133.

Rajihy, Y., Nermend, K., & Alsakaa, A. (2017). Back-propagation artificial neural networks in stock market forecasting. an application to the Warsaw stock exchange WIG20.Aestimatio ,(15), 88-99. doi: 10.5605/IEB.15.5

Riepe, M. W., C.F.A., & Iachini, Michael, C.F.A., C.F.P. (2011). Volume and assets as determinants of ETF bid-ask spreads.Journal of Financial Planning ,24(5), 32-33,40.

Rompotis, G. G. (2011). Predictable patterns in ETFs' return and tracking error. Studies in Economics and Finance ,28(1), 14-35. doi: 10.1108/10867371111110534

Sanchez, B., & Wei, P. (2010). The liquidity of exchange traded funds. International Review of Applied Financial Issues and Economics ,2(4), 621-646.

Sánchez, F. J. Z., Ovalle, R. I. A., Ramos, D. S., Alba, J. A. V., & García, F.,R.T. (2012). Una estrategia para portafolios con fondos cotizados */A strategy for exchange traded funds (ETFs) portfolios.Revista Española De Financiación y Contabilidad ,41(155), 417-444.

Scozzari, A., Tardella, F., Paterlini, S., & Krink, T. (2013). Exact and heuristic approaches for the index tracking problem with UCITS constraints. Annals of Operations Research ,205(1), 235-250. doi: 10.1007/s10479-012-1207-1

Shanno, D. (1970), "Conditioning of quasi-Newton methods for function minimization", Mathematics of Computation , 24 (111): 647-656, doi:10.1090/S0025-5718-1970-0274029-X, MR 0274029

Shanno, D.; Kettler, P.(1970), "Optimal conditioning of quasi-Newton methods", Mathematics of Computation , 24 (111): 657-664, doi:10.1090/S0025-5718-1970-0274030-6, MR 0274030

Sharifzadeh, M., & Hojat, S. (2012). An analytical performance comparison of exchange-traded funds with index funds: 2002-2010.Journal of Asset Management ,13(3), 196-209. doi: 10.1057/jam.2012.3

Sharma, D. K., & Rababaah, A. R. (2014). Stock market predictive model based on integration of signal processing and artificial neural network.Academy of Information and Management Sciences Journal ,17(1), 51-70.

Shiller, R. (2003). "From Efficient Markets Theory to Behavioral Finance."Journal of Economic Perspectives,17 (1): 83-104.

Schizas, P. (2014). Active ETFs and their performance vis-à-vis passive ETFs, mutual funds, and hedge funds.The Journal of Wealth Management ,17(3), 84-98,6-7.

Shum, P. M., & Kang, J. (2013). Leveraged and inverse ETF performance during the financial crisis.Managerial Finance ,39(5), 476-508. doi: 10.1108/03074351311313825

Thaler, R. H. (2015). Misbehaving: The making of behavioral economics. New York: W.W. Norton & Company, [2015]

Tseng, Y., & Lee, W. (2016). Investor sentiment and ETF liquidity - evidence from Asia markets.Advances in Management and Applied Economics ,6(1), 89-111.

Vaishy, N., & Lavanya, K. (2016). Stock market prediction by non-linear combination based on support vector machine regression model. International Journal of Advanced Research in Computer Science ,7(7) [ Links ]

Vejendla, A., & Enke, D. (2013). Performance evaluation of neural networks and garch models for forecasting volatility and option strike prices in a bull call spread strategy.Journal of Economic Policy and Research ,8(2), 1-19.

Williams, S. O. (2014). Country ETFs, currencies and international diversification. Journal of Asset Management ,15(6), 392-414. doi: 10.1057/jam.2014.28

Yamori, N. (2011). Commodity ETFs in the Japanese Stock Exchanges. Journal of Advanced Studies in Finance ,2(1), 11-12.

Publicado
2019-07-03
Sección
Artículos Originales