Static, Dynamic, and Hybrid Neural Networks in Forecasting Inflation

Authors:
Saeed Moshiri;Norman E. Cameron;David Scuse
Affiliations:
Department of Economics, University of Winnipeg, Winnipeg, Manitoba, Canada R3B 2E9 E-mail: smoshiri@io.uwinnipeg.ca;Department of Economics, University of Winnipeg, Winnipeg, Manitoba, Canada R3B 2E9 E-mail: smoshiri@io.uwinnipeg.ca;Department of Economics, University of Winnipeg, Winnipeg, Manitoba, Canada R3B 2E9 E-mail: smoshiri@io.uwinnipeg.ca
Venue:
Computational Economics
Year:
1999

Citing 4
Cited 2

Layered neural networks with Gaussian hidden units as universal approximations

Neural Computation
Neural network models for time series forecasts

Management Science
Advanced Methods in Neural Computing

Advanced Methods in Neural Computing
Neural Networks in Finance and Investing: Using Artificial Intelligence to Improve Real World Performance

Neural Networks in Finance and Investing: Using Artificial Intelligence to Improve Real World Performance

CO$^2$RBFN for short-term forecasting of the extra virgin olive oil price in the Spanish market

International Journal of Hybrid Intelligent Systems - Hybrid Fuzzy Models
A study on the medium-term forecasting using exogenous variable selection of the extra-virgin olive oil with soft computing methods

Applied Intelligence

Quantified Score

Hi-index	0.01

Visualization

Abstract

The back-propagation neural network (BPN) model has been the most popular formof artificial neural network model used for forecasting, particularly ineconomics and finance. It is a static (feed-forward) model which has alearning process in both hidden and output layers. In this paper we comparethe performance of the BPN model with that of two other neural network models,viz., the radial basis function network (RBFN) model and the recurrent neuralnetwork (RNN) model, in the context of forecasting inflation. The RBFN modelis a hybrid model with a learning process that is much faster than the BPNmodel and that is able to generate almost the same results as the BPN model.The RNN model is a dynamic model which allows feedback from other layers tothe 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 econometrictime series models.