Premium
Forecasting time‐dependent conditional densities: a semi non‐parametric neural network approach
Author(s) -
Schittenkopf Christian,
Dorffner Georg,
Dockner Engelbert J.
Publication year - 2000
Publication title -
journal of forecasting
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.543
H-Index - 59
eISSN - 1099-131X
pISSN - 0277-6693
DOI - 10.1002/1099-131x(200007)19:4<355::aid-for778>3.0.co;2-z
Subject(s) - autoregressive conditional heteroskedasticity , conditional variance , econometrics , volatility (finance) , artificial neural network , conditional probability distribution , conditional expectation , time series , computer science , series (stratigraphy) , parametric statistics , economics , mathematics , statistics , artificial intelligence , machine learning , paleontology , biology
In financial 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 modelling 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 100 data demonstrates the importance of distributional assumptions in volatility prediction and shows that the out‐of‐sample forecasting performance of neural networks slightly dominates those of GARCH models. Copyright © 2000 John Wiley & Sons, Ltd.