COMPARISON OF ASYMMETRIC GARCH MODELS WITH ARTIFICIAL NEURAL NETWORK FOR STOCK MARKETS PREDICTION, A CASE STUDY

  • Samreen Fatima University of Karachi, Pakistan
Keywords: A-GARCH (Asymmetric GARCH), EGARCH (Exponential GARCH), PGARCH (Power GARCH), ANN (Artificial neural networks)

Abstract

Much efforts have been done for modeling of financial data theoretically and empirically for the international
stock markets, for example: Asia, Europe and Australia etc. But no frequent research has been done for the SAARC
countries stock markets. Therefore, bench mark Index of Pakistan; Karachi Stock Exchange (KSE-100) and Bombay
Stock Exchange (BSNSE) of India are selected as case study. They are not only the member of SAARC but also sharing
the common border, due to this they are also involving in bilateral trading. We used closing indices of daily share
price for the period of 1st January, 2010 to 15th January 2016. This study compares the forecasting performance
and also investigates more volatile stock markets using Asymmetric GARCH (A-GARCH) models and non-parametric
method (Artificial Neural Networks). In the A-GARCH; EGARCH and PGARCH models are used. Firstly, suitable
Asymmetric GARCH (A-GARCH) model was developed for forecasting and investigating leverage effect. Secondly,
an Artificial Neural Networks model was developed for the said stock markets. Lastly, forecasting performance of the
FA-GARCH and ANN models both in and out sample were evaluated using root mean square error. In the A-GARCH;
EGARCH (1,1) performed better than PGARCH(1,1) in both stock market data. However, when comparing A-GARCH
with ANN, it was found that ANN gave minimum out sample forecasting error as compared to A-GARCH models.
Therefore, ANN out played other studied models.

References

1. Mandelbrot,(1963), “ The variation of certain speculative
prices”, J. of Business, vol. 36, pp. 394-419.
2. Black, F., (1976), “ Studies of Stock Prices Volatility
Changes”, Proceedings of 1976 Meetings of the
American Statistical Association, Business and
Economic Statistics Section, (1976),pp. 177-181.
3. Engle, R.F., (1982), “Autoregressive Conditional
Heteroskedasticity with estimates of the varianceof United Kingdom inflation”, J. Econometrica, vol.
50, pp. 987–1007.
4. Bollerslev, T., (1986), “Generalized Autoregressive
Conditional Heteroskedasticity”, J. Econometrics,
vol. 31, pp. 307–327.
5. Nelson, D. B., (1991), “Conditional Heteroscedasticity
In Asset Returns, A New Approach”, Econometrica,
pp. 347-370.
6. Glosten, L., Jagannathan, R., and Runkle, D., (1993),
“On the Relation between the Expected Value and the
Volatility of the Nominal Excess Return on Stocks”,
J. of Finance ,vol. 48, pp.1779 – 1801.
7. Ding, Z., Granger, C.W.J., and Engle, R.F., (1993),
“A long memory property of stock market returns
and a new model”, Journal of Empirical Finance,
vol. 1, pp. 83–106.
8. Zakoian, J. M., (1994), “Threshold heteroskedastic
models”, J. of Economic Dynamics and Control,
vol. 18, pp. 931-955.
9. Samreen, F., (2008), “ARCH-M Model for Benchmark
Index of Pakistan Stock Market”, Published in 4th
National Conference of Islamic Countries on statistical
Sciences (ISOSS), May 10-12, pp. 51-54.
10. Zafar Muhmud, (2000), “Bayesian Forecasting using
nonlinear time series models”, J. Engg. and Appl.
Sci. vol. 19(1), pp. 169-173.
11. Abraham, A., and Nath, B., (2001), “A Neouro
fuzzy Approach For Modeling Electricity Demand
In Victoria”, J. Appl. Soft Computing, vol. 1,
pp.127-138.
12. Delen, D., Waller, G., and Kadam, A., (2005),
“Predicting Breast Cancer Survivability, A
Comparison of Three Data Mining Methods”, J.
Artificial Intelligence In Medicine, vol. 34, pp.
113-127.
13. Ganeta, R., Romeo, L.M., and Gill, A., (2006),
“Forecasting of Electricity Prices with Neural
Networks”, Energy Conversion and Managementvol .47, pp. 1770-1778.
14. Greg, T., and Sarah, Hu., (1999), “Forecasting GDP
growth using artificial neural network”, Working
paper, Bank of Canada, /http://www.bankofcanada.
ca/ en/res/wp/1999/wp99-3.pdfS.
15. Srinivasulu, S., and Jain, A., (2006), “A Comparative
Analysis of training methods for ANN Rainfall-
Runoff Models”, J. Appl. Soft Computing , vol. 6
, pp. 295-306.
16. Kulsoom,I., Shahzad, A., Izhar ul, H., Tahir, M. K.,
Riaz, S. A., (2016), “An optimal neural network
based classification technique for breast cancer
detection”, J. Engg. and Appl. Sci. Vol. 35 (1), pp
.51-58.
17. Sahar Noor, Khan, M. K., Hussain, I., Khan, A.,
Syed, R. A. S., Shah, W., and Babar, M. I., (2009),
“Application of a Hybrid Artificial Neural Networks
Model to a Scheduling Policy System”, J. Engg. and
Appl. Sci. Vol. 28(1), pp. 89-102.
18. Samreen, F., and Ghulam, H., (2002), “On forecasting
KSE100 index on daily returns using Artificial
Neural Networks”, A comparative study. Published
in 8th Statistics proceeding of Karachi University,
December ,2002.
19. Samreen, F., and Ghulam, H., (2008), “Statistical
models of KSE100 index using Hybrid Financial
Systems”, Extended Paper, Int. J. of Neurocomputing,
vol. 71, pp. 2742-2746 .
20. Zivot, Eric, (2009), “Practical Issues in the Analysis
of Univariate GARCH Models”, In: T.G. Andersen,
RA Davis, J-P Kreis and T Mikosch (Edts.),
Handbook of Financial Time Series, Springer, New
York, Springer, pp. 113–155.
21. Mehdi Khashei, Zeinal, A. H., and Mehdi B., (2012),
“A novel hybrid classification model of artificial
neural networks and multiple linear regression
models Expert Systems with Applications”, vol. 39,
pp.2606–2620.
22. Zhang, G., Patuwo, B. E., and Hu, M.Y., (1998),
“Forecasting with artificial neural networks: The
state of the art”, Int. J. of Forecasting, vol.14 (1)
pp. 35–62.
Published
2017-11-20