Not Available for Download

Forecasting Gold Price Changes: Rolling and Recursive Neural Network Models

Journal of Multinational Financial Management, Vol. 18, No. 5, pp. 477-487, 2008

Posted: 30 Jul 2011  

Antonino Parisi

affiliation not provided to SSRN

Franco Parisi

University of Chile

David Diaz

Universidad de Chile - Escuela de Economia y Negocios

Date Written: November 26, 2007

Abstract

This paper analyzes recursive and rolling neural network models to forecast one-step-ahead sign variations in gold price. Different combinations of techniques and sample sizes are studied for feed forward and ward neural networks. The results shows the rolling ward networks exceed the recursive ward networks and feed forward networks in forecasting gold price sign variation. The results support the use of neural networks with a dynamic framework to forecast the gold price sign variations, recalculating the weights of the network on a period-by-period basis, through a rolling process. Our results are validated using the block bootstrap methodology with an average sign prediction of 60.68% with a standard deviation of 2.82% for the rolling ward net.

Keywords: Recursive operation; Rolling operation; Artificial neural networks

JEL Classification: G10; G14; G15

Suggested Citation

Parisi, Antonino and Parisi, Franco and Diaz, David, Forecasting Gold Price Changes: Rolling and Recursive Neural Network Models (November 26, 2007). Journal of Multinational Financial Management, Vol. 18, No. 5, pp. 477-487, 2008. Available at SSRN: https://ssrn.com/abstract=1898700

Antonino Parisi

affiliation not provided to SSRN ( email )

Franco Parisi

University of Chile ( email )

Department of Finance Oficina 1102
Santiago
Chile
+56 2 678-3366 (Phone)
+56 2 222-0639 (Fax)

David Diaz (Contact Author)

Universidad de Chile - Escuela de Economia y Negocios ( email )

Diagonal Paraguay 257
oficina 1102
Santiago, RM 0000
Chile
5629783373 (Phone)

Paper statistics

Abstract Views
979