Forecasting Time-dependent Conditional Densities: A Semi-non- parametric Neural Network Approach

In _nancial econometrics the modelling of asset return series is closely related to the estimation of the corresponding conditional densities[ One reason why one is interested in the whole conditional density and not only in the conditional mean is that the conditional variance can be interpreted as a measure of time!dependent volatility of the return series[ In fact\ the mod! elling and the prediction of volatility is one of the central topics in asset pricing[ In this paper we propose to estimate conditional densities semi! non!parametrically in a neural network framework[ Our recurrent mixture density networks realize the basic ideas of prominent GARCH approaches but they are capable of modelling any continuous conditional density also allowing for time!dependent higher!order moments[ Our empirical analysis of daily FTSE 099 data demonstrates the importance of distributional assumptions in volatility prediction and shows that the out!of!sample fore! casting performance of neural networks slightly dominates those of GARCH models[ Copyright 1999 John Wiley + Sons\ Ltd[

[1]  B. Mandlebrot The Variation of Certain Speculative Prices , 1963 .

[2]  E. Fama The Behavior of Stock-Market Prices , 1965 .

[3]  F. Black,et al.  The Pricing of Options and Corporate Liabilities , 1973, Journal of Political Economy.

[4]  Richard J. Rendleman,et al.  STANDARD DEVIATIONS OF STOCK PRICE RATIOS IMPLIED IN OPTION PRICES , 1976 .

[5]  R. Engle Autoregressive conditional heteroscedasticity with estimates of the variance of United Kingdom inflation , 1982 .

[6]  T. Bollerslev,et al.  Generalized autoregressive conditional heteroskedasticity , 1986 .

[7]  A. Lapedes,et al.  Nonlinear signal processing using neural networks: Prediction and system modelling , 1987 .

[8]  T. Bollerslev,et al.  A CONDITIONALLY HETEROSKEDASTIC TIME SERIES MODEL FOR SPECULATIVE PRICES AND RATES OF RETURN , 1987 .

[9]  Geoffrey J. McLachlan,et al.  Mixture models : inference and applications to clustering , 1989 .

[10]  P. J. Green,et al.  Density Estimation for Statistics and Data Analysis , 1987 .

[11]  A. Gallant,et al.  Seminonparametric Estimation Of Conditionally Constrained Heterogeneous Processes: Asset Pricing Applications , 1989 .

[12]  Adrian Pagan,et al.  Alternative Models for Conditional Stock Volatility , 1989 .

[13]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[14]  Anders Krogh,et al.  Introduction to the theory of neural computation , 1994, The advanced book program.

[15]  Daniel B. Nelson CONDITIONAL HETEROSKEDASTICITY IN ASSET RETURNS: A NEW APPROACH , 1991 .

[16]  R. Chou,et al.  ARCH modeling in finance: A review of the theory and empirical evidence , 1992 .

[17]  Russell Reed,et al.  Pruning algorithms-a survey , 1993, IEEE Trans. Neural Networks.

[18]  L. Glosten,et al.  On the Relation between the Expected Value and the Volatility of the Nominal Excess Return on Stocks , 1993 .

[19]  Christopher G. Lamoureux,et al.  Forecasting Stock-Return Variance: Toward an Understanding of Stochastic Implied Volatilities , 1993 .

[20]  Heekuck Oh,et al.  Neural Networks for Pattern Recognition , 1993, Adv. Comput..

[21]  Anil K. Bera,et al.  ARCH Models: Properties, Estimation and Testing , 1993 .

[22]  I. Kneppo,et al.  Measuring and Testing , 1994 .

[23]  A. Refenes Neural Networks in the Capital Markets , 1994 .

[24]  Ralph Neuneier,et al.  Estimation of Conditional Densities: A Comparison of Neural Network Approaches , 1994 .

[25]  R. Engle,et al.  Forecasting Volatility and Option Prices of the S&P 500 Index , 1994 .

[26]  Raúl Rojas,et al.  Neural Networks - A Systematic Introduction , 1996 .

[27]  Ralph Neuneier,et al.  Experiments in predicting the German stock index DAX with density estimating neural networks , 1996, IEEE/IAFE 1996 Conference on Computational Intelligence for Financial Engineering (CIFEr).

[28]  C. Schmitt,et al.  Delta-neutral volatility trading with intra-day prices: an application to options on the DAX , 1996 .

[29]  Jacob Boudoukh,et al.  Investigation of a Class of Volatility Estimators , 1997 .

[30]  R. Donaldson,et al.  An artificial neural network-GARCH model for international stock return volatility , 1997 .

[31]  N. Burgess,et al.  Modelling market volatilities: the neural network perspective , 1997 .

[32]  E. Dockner,et al.  Volatility Prediction with Mixture Density Networks , 1998 .

[33]  Fred Collopy,et al.  How effective are neural networks at forecasting and prediction? A review and evaluation , 1998 .

[34]  T. Bollerslev,et al.  ANSWERING THE SKEPTICS: YES, STANDARD VOLATILITY MODELS DO PROVIDE ACCURATE FORECASTS* , 1998 .

[35]  Dirk Ormoneit Probability estimating neural networks , 1998 .

[36]  J. C. Sosa On the informational content of implied volatility , 2000 .

[37]  Yacine Aït-Sahalia,et al.  Do option markets correctly price the probabilities of movement of the underlying asset , 2001 .

[38]  Stephen Gray,et al.  Semiparametric ARCH models , 2001 .

[39]  William H. Press,et al.  Numerical recipes in C , 2002 .