- Author
- Capobianco Enrico (Parallel Distributed Processing Research Group at Stanford University)
- Title
- Artificial Neural Networks for Volatility Models
Sztuczne sieci neuronowe dla modeli zmienności - Source
- Badania Operacyjne i Decyzje, 1999, nr 2, s. 15-25, bibliogr. 11 poz.
Operations Research and Decisions - Keyword
- Sieci neuronowe, Sztuczne sieci neuronowe (SSN), Szeregi czasowe
Neural networks, Artificial neural networks (ANN), Time-series - Note
- summ., streszcz.
- Abstract
- W artykule przedstawiono pobieżnie ideę modeli typu ARCH, a także idę sztucznych sieci neuronowych. Modele rodziny ARCH umożliwiają wykorzystanie do prognozowania warunkowych momentów rzędu wyższego niż jeden. Sieci neuronowe zaś charakteryzują się dużymi możliwościami aproksymacji funkcji. Przedstawiono próbę zbudowania modelu łączącego zalety modeli ARCH i sieci neuronowych. (abstrakt oryginalny)
This paper presents an extension to backpropagation networks for financial time series prediction. We want the network that uses the information carried by the first and second order conditional moments of the distribution of interest, so as to combine its built-in nonlinear features with the typical dependence implied by ARCH-type and Stochastic Volatility models, whose effects must be estimated. A likelihood-type performance measure is discussed and learning schemes are suggested for conditionally Gaussian models. (original abstract) - Accessibility
- The Main Library of the Cracow University of Economics
The Library of Warsaw School of Economics - Bibliography
-
- BOLLERSLEV T.P., Generalized Autoregressive Conditional Heteroscedasticity, Journal of Econometrics 1986, 31, 309-328.
- BOLLERSLEV T.P., CHOU R.Y., KRONER K., ARCH modelling in finance: a review of the theory and empirical evidence, Journal of Econometrics 1992, 52, 5-59.
- ENGLE R.F., Autoregressive Conditional Heteroscedasticity with estimates of the variance of U.K. inflation, Econometrica 1982, 50, 987-1008.
- LIN T., HORNE B.G., GILES C.L., How embedded memory in recurrent neural network architectures helps learning long-term temporal dependencies, CS-TR-3626 and UMIACS-TR-96-28, University of Maryland, 1996.
- HARVEY A.C., Time Series Models, The MIT Press, Cambridge, MA, second edition, 1993.
- KUAN C.M., LIU T., Forecasting exchange rates using feedforward and recurrent neural networks, Journal of Applied Econometrics 1995, 10, 347-364.
- PHAM D.T., LIU X., Neural Networks for Identification, Prediction and Control, London, Springer-Verlag, UK, 1995.
- RUMELHART D.E., MCCLELLAND J.L. and the PDP Research Group, Parallel Distributed Processing: Explorations in the Microstructure of Cognition 1986, Vol. 1, MIT Press: Cambridge, MA.
- TAYLOR S., Modelling Financial Time Series, New York, Wiley and Sons, NY, 1986.
- WEIGEND A.S., GERSHENFELD N.A., Time series prediction: forecasting the future and understanding the past, Proceedings of the NATO Adv. Res. Works. on Comp. Time Ser. Anal. held in Santa Fe, Addison-Wesley, New Mexico, 1992.
- WEIGEND A.S., NIX D.A., Predictions with confidence intervals (local error bars), Proceedings of ICONIP'94, Seoul, Korea, 1994, 847-852.
- Cited by
- ISSN
- 1230-1868
- Language
- eng
