Static, Dynamic, and Hybrid Neural Networks in Forecasting Inflation

Computational Economics, Forthcoming

17 Pages Posted: 25 Aug 1998 Last revised: 4 Oct 2013

See all articles by Saeed Moshiri

Saeed Moshiri

Saint Thomas More College University of Saskatcehwan

Norman Edward Cameron

University of Manitoba - Department of Economics

David Scuse

University of Manitoba - Department of Computer Science

Date Written: November 24, 1998

Abstract

The back-propagation neural network (BPN) model has been the most popular form of artificial neural network model used for forecasting, particularly in economics and finance. It is a static (feed-forward) model which has a learning process in both hidden and output layers. In this paper, we compare the performance of the BPN model with that of two other neural network models, i.e., radial basis function network (RBFN) model and recurrent neural network (RNN) model, in the context of forecasting inflation. The RBFN model is a hybrid model whose learning process is much faster than the BPN model and able to generate almost the same results as the BPN model. The RNN model is a dynamic model which allows feedback from other layers to input layer, enabling it to capture the dynamic behavior of the series. The results of the ANN models are also compared with those of the econometric time series models.

JEL Classification: C22, C45, E31, E37

Suggested Citation

Moshiri, Saeed and Cameron, Norman Edward and Scuse, David, Static, Dynamic, and Hybrid Neural Networks in Forecasting Inflation (November 24, 1998). Computational Economics, Forthcoming. Available at SSRN: https://ssrn.com/abstract=114029

Saeed Moshiri (Contact Author)

Saint Thomas More College University of Saskatcehwan ( email )

1437 College Dr
Saskatoon, Saskatchewan S7N 0W6
Canada

Norman Edward Cameron

University of Manitoba - Department of Economics ( email )

Winnipeg, Manitoba R3T 5V5
Canada

David Scuse

University of Manitoba - Department of Computer Science ( email )

Canada
204-474-9207 (Phone)
204-474-7681 (Fax)

Register to save articles to
your library

Register

Paper statistics

Downloads
32
Abstract Views
1,542
PlumX Metrics