Can neural network model selection be guided by statistical procedures such as hypothesis tests, information criteria and cross-validation? Recently, Anders and Korn (1999) proposed five neural network model specification strategies based on different statistical procedures. In this paper, we use and adapt the Anders-Korn framework to find appropriate neural network models for financial time series prediction. The most important new issue in this context is the specification of the dynamic structure of the models, i.e. the selection ofthe lagged values ofthe input time series. A linear model is built with full dynamic structure, then its possible nonlinear extensions are tested using a statistical procedure inspired by the Anders-Kom approach. Promising results are obtained with an application to predict the monthly time series of mortgage loans purchased in The Netherlands.

Neural Network Model Selection for Financial Time Series Prediction.

VIRILI, Francesco;
2001-01-01

Abstract

Can neural network model selection be guided by statistical procedures such as hypothesis tests, information criteria and cross-validation? Recently, Anders and Korn (1999) proposed five neural network model specification strategies based on different statistical procedures. In this paper, we use and adapt the Anders-Korn framework to find appropriate neural network models for financial time series prediction. The most important new issue in this context is the specification of the dynamic structure of the models, i.e. the selection ofthe lagged values ofthe input time series. A linear model is built with full dynamic structure, then its possible nonlinear extensions are tested using a statistical procedure inspired by the Anders-Kom approach. Promising results are obtained with an application to predict the monthly time series of mortgage loans purchased in The Netherlands.
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11580/9731
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
social impact