Abstract
Optimal portfolio allocation is one of the most important practical problems in financial engineering. The portfolio optimization problem and traditional approach were first initiated by Markowitz in which investors construct a portfolio with a minimum risk for a specified return. The most critical assumption of the Markowitz model is that returns are assumed to be normally distributed. In practice, returns usually do not follow a normal distribution and have heavy tails. Furthermore, forecasting returns and volatilities of assets are essential tasks in the financial market and portfolio optimization. In this paper, we use stable distribution to capture non-normal and skewness properties of asset returns and utilize the traditional econometric ARMA-GARCH model incorporating the Artificial Neural Networks model to predict returns and volatilities of assets on the Vietnam stock market. We then construct an optimal portfolio selection problem. Our main results indicate that the proposed model outperforms the market index (VN30) and traditional econometric models in terms of both risk and return.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Aggarwal, C.C.: Neural Networks and Deep Learning. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-94463-0
Berger, T.: Forecasting value-at-risk using time varying copulas and EVT return distributions. Int. Econ. 133, 93–106 (2013)
Hajizadeh, E., Seifi, A., Zarandi, M.H.F., Turksen, I.B.: A hybrid modeling approach for forecasting the volatility of S &P 500 index return. Exp. Syst. Appl. 39, 431–436 (2012)
Farma, E.: Mandelbrot and the stable paretian hypothesis. J. Bus. 36(4), 420–429 (1963)
Huang, C.-W., Hsu, C.-P.: Portfolio optimization with GARCH-EVT-Copula-CVaR models. Bank. Finan. Rev. 7(1), 19–31 (2015)
Karmakar, M.: Dependence structure and portfolio risk in Indian foreign exchange market: a GARCH-EVT-Copula approach. Q. Rev. Econ. Finan. 64, 275–291 (2017)
Kim, H.Y., Won, C.H.: Forecasting the volatility of stock price index: a hybrid model integrating LSTM with multiple GARCH-type models. Exp. Syst. Appl. 103, 25–37 (2018)
Krezolek, D.: The application of alpha-stable distributions in portfolio selection problem-the case of metal market. Studia Ekonomiczne 247, 57–68 (2015)
Mandelbrot, B.: The variation of certain speculative prices. J. Bus. 36(4), 394–419 (1963)
Markowitz, H.: Portfolio selection. J. Finan. 7(1), 77–91 (1952)
Rachev, S., Han, S.: Portfolio management with stable distributions. Math. Meth. Oper. Res. 51, 341–352 (2000)
Sahamkhadam, M., Stephan, A., Östermark, R.: Portfolio optimization based on GARCH-EVT-Copula forecasting models. Int. J. Forecast. 34(3), 497–506 (2018)
Stay, R.: Analysis of Financial Time Series, 3rd edn. Wiley (2010)
Vasiukevich, A., Pinsky, E.: Constructing portfolios using stable distributions: the case of S &P 500 sectors exchange-traded funds. Mach. Learn. Appl. 10, 10034 (2022)
Yu, S.L., Li, Z.: Forecasting stock price index volatility with LSTM deep neural network. In: Tavana, M., Patnaik, S. (eds.) Recent Developments in Data Science and Business Analytics. SPBE, pp. 265–272. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-72745-5_29
Zhang, G.P.: Time series forecasting using a hybrid ARIMA and neural network model. Neurocomputing 50, 159–175 (2003)
Zhong, X., Enke, D.: Predicting the daily return direction of the stock market using hybrid machine learning algorithms. Finan. Innov. 5(24), 1–20 (2019)
Acknowledgements
We would like to thank Professor Hung T. Nguyen for his enthusiasm and for introducing new directions in the field of statistics. This research is funded by International University, VNU-HCM under grant number SV2022-MA-02.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Anh, N.T., Lam, M.D., Ta, B.Q. (2023). Mean-Variance Portfolio Allocation Using ARMA-GARCH-Stable and Artificial Neural Network Models. In: Huynh, VN., Le, B., Honda, K., Inuiguchi, M., Kohda, Y. (eds) Integrated Uncertainty in Knowledge Modelling and Decision Making. IUKM 2023. Lecture Notes in Computer Science(), vol 14375. Springer, Cham. https://doi.org/10.1007/978-3-031-46775-2_16
Download citation
DOI: https://doi.org/10.1007/978-3-031-46775-2_16
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-46774-5
Online ISBN: 978-3-031-46775-2
eBook Packages: Computer ScienceComputer Science (R0)