ISCIS 2003: Computer and Information Sciences - ISCIS 2003 pp 553-560 | Cite as
Financial Time Series Prediction Using Mixture of Experts
Abstract
This paper investigates the use of artificial neural networks (ANN) in risk estimation of asset returns. Istanbul Stock Exchange (ISE) index (XU100) is studied with a mixture of experts ANN architecture using daily data over a 12-year period. Results are compared to feed-forward neural networks, multilayer perceptron (MLP) and radial basis function (RBF) networks and recurrent neural networks (RNN). They are also compared to widely accepted Exponential Generalized Autoregressive Conditional Heteroskedasticity (EGARCH) volatility model. These results suggest that mixture of experts (MoE) have the strength to capture the volatility in index return series and prepares a valuable basis for financial decision making.
Keywords
Root Mean Square Error Mean Square Error Radial Basis Function Recurrent Neural Network Hide UnitPreview
Unable to display preview. Download preview PDF.
References
- 1.Schittenkopf, C., Dorffner, G.: Risk Neutral Density Extraction from Option Prices: Improved Pricing with Mixture Density Networks (1999)Google Scholar
- 2.Tino, P., Schittenkopf, C., Dorffner, G.: Volatility Trading via Temporal Pattern Recognition in Quantized Financial Time Series (2000)Google Scholar
- 3.Chan, L., Gao, X.: An Algorithm for Trading and Portfolio Management Using Q-learning and Sharpe Ratio Maximization. In: Proceedings of International Conference on Neural Information Processing, ICONIP 2000, Taejon, Korea, pp. 832–837.Google Scholar
- 4.Hellstrom, T., Holmstrom, K.: Predictable Pattern in Stock Returns, Technical Report Series, IMA-TOM (1997–09)Google Scholar
- 5.Yao, J.T., Tan, C.L.: Guidelines for Financial Forecasting with Neural Networks (2001)Google Scholar
- 6.Engle, R.: Autoregressive Conditional Heteroskedasticity with estimates of the variance of United Kingdom inflation. Econometrica 50, 987–1007 (1982)MATHCrossRefMathSciNetGoogle Scholar
- 7.Bollerslev, T.: Generalized Autoregressive Conditional Heteroskedasticity. Journal of Econometrics 31, 307–327 (1986)MATHCrossRefMathSciNetGoogle Scholar
- 8.Nelson, D.: Conditional Heteroskedasticity in asset returns: a new approach. Econometrica 59, 349–370 (1991)CrossRefGoogle Scholar
- 9.Engle, R.F., Ng, V.K.: Measuring and Testing the Impact of News on Volatility. The Journal of Finance 48(5), 1749–1778 (1993)CrossRefGoogle Scholar
- 10.Okay, N.: Asymmetric Volatility Dynamics: Evidence From The Istanbul Stock Exchange, Business & Economics for the 21st Century, vol II, B&ESI, pp. 207–216 (1998)Google Scholar
- 11.Okay, N.: Evidence For Conditional Heteroskedasticity in Turkish Stock Returns. In: Readings Book of the 1998 ABA National Conference, pp. 241–247 (1998)Google Scholar
- 12.Bera, A.K., Higgins, M.L.: Arch Models. Properties, Estimation and testing. Journal of Economic Surveys 7, 305–362 (1993)CrossRefGoogle Scholar
- 13.Okay, N.: Dynamic predictability of the Istanbul Stock Exchange Market using a Vector Autoregressive Model. Bogazici Journal 12, 31–56Google Scholar
- 14.Jacobs, R.A., Jordan, M.I., Nowlan, S.J., Hinton, G.E.: Adaptive mixture of local experts. Neural Computation 3, 79–87 (1991)CrossRefGoogle Scholar