hrcak mascot   Srce   HID

Croatian Operational Research Review, Vol. 5 No. 2, 2014.

Izvorni znanstveni članak
https://doi.org/10.17535/crorr.2014.0017

GARCH based artificial neural networks in forecasting conditional variance of stock returns

Josip Arnerić   ORCID icon orcid.org/0000-0002-2901-2609 ; Faculty of Economics and Business, University of Zagreb
Tea Poklepović   ORCID icon orcid.org/0000-0002-6279-6070 ; Faculty of Economics, University of Split
Zdravka Aljinović   ORCID icon orcid.org/0000-0002-9133-0149 ; Faculty of Economics, University of Split

Puni tekst: engleski, pdf (377 KB) str. 329-343 preuzimanja: 2.449* citiraj
APA 6th Edition
Arnerić, J., Poklepović, T. i Aljinović, Z. (2014). GARCH based artificial neural networks in forecasting conditional variance of stock returns. Croatian Operational Research Review, 5 (2), 329-343. https://doi.org/10.17535/crorr.2014.0017
MLA 8th Edition
Arnerić, Josip, et al. "GARCH based artificial neural networks in forecasting conditional variance of stock returns." Croatian Operational Research Review, vol. 5, br. 2, 2014, str. 329-343. https://doi.org/10.17535/crorr.2014.0017. Citirano 22.02.2019.
Chicago 17th Edition
Arnerić, Josip, Tea Poklepović i Zdravka Aljinović. "GARCH based artificial neural networks in forecasting conditional variance of stock returns." Croatian Operational Research Review 5, br. 2 (2014): 329-343. https://doi.org/10.17535/crorr.2014.0017
Harvard
Arnerić, J., Poklepović, T., i Aljinović, Z. (2014). 'GARCH based artificial neural networks in forecasting conditional variance of stock returns', Croatian Operational Research Review, 5(2), str. 329-343. doi: https://doi.org/10.17535/crorr.2014.0017
Vancouver
Arnerić J, Poklepović T, Aljinović Z. GARCH based artificial neural networks in forecasting conditional variance of stock returns. Croatian Operational Research Review [Internet]. 2014 [pristupljeno 22.02.2019.];5(2):329-343. doi: https://doi.org/10.17535/crorr.2014.0017
IEEE
J. Arnerić, T. Poklepović i Z. Aljinović, "GARCH based artificial neural networks in forecasting conditional variance of stock returns", Croatian Operational Research Review, vol.5, br. 2, str. 329-343, 2014. [Online]. doi: https://doi.org/10.17535/crorr.2014.0017

Sažetak
Portfolio managers, option traders and market makers are all interested in volatility forecasting in order to get higher profits or less risky positions. Based on the fact that volatility is time varying in high frequency data and that periods of high volatility tend to cluster, the most popular models in modelling volatility are GARCH type models because they can account excess kurtosis and asymmetric effects of financial time series. A standard GARCH(1,1) model usually indicates high persistence in the conditional variance, which may originate from structural changes. The first objective of this paper is to develop a parsimonious neural networks (NN) model, which can capture the nonlinear relationship between past return innovations and conditional variance. Therefore, the goal is to develop a neural network with an appropriate recurrent connection in the context of nonlinear ARMA models, i.e., the Jordan neural network (JNN). The second objective of this paper is to determine if JNN outperforms the standard GARCH model. Out-of-sample forecasts of the JNN and the GARCH model will be compared to determine their predictive accuracy. The data set consists of returns of the CROBEX index daily closing prices obtained from the Zagreb Stock Exchange. The results indicate that the selected JNN(1,1,1) model has superior performances compared to the standard GARCH(1,1) model. The contribution of this paper can be seen in determining the appropriate NN that is comparable to the standard GARCH(1,1) model and its application in forecasting conditional variance of stock returns. Moreover, from the econometric perspective, NN models are used as a semi-parametric method that combines flexibility of nonparametric methods and the interpretability of parameters of parametric methods.

Ključne riječi
conditional variance; GARCH; NN; forecast error; volatility persistence

Hrčak ID: 133783

URI
https://hrcak.srce.hr/133783

Posjeta: 2.718 *