Conference proceeding
Comparative study of the predictive accuracy of multilayer perceptron networks versus simple recurrent networks for selecting forecasting methods
The 1997 Annual Meeting of the Decision Sciences Institute. Part 1 (of 3); San Diego, CA; USA; 22-25 Nov. 1997, pp.373-375
22 Nov 1997
Abstract
Forecasting is an important and necessary activity for all types of organizations. Selecting a forecasting model is a complex and time-consuming task. This research describes the use of two Artificial Neural Network topologies namely, Multilayer Perceptron and Simple Recurrent Networks to predict the most accurate forecasting model for any given time series. Econometric time series datasets were used to train and test the ANNs. The results of this experiment, which appear promising are presented together with guidelines for its practical application. Potential benefits include dramatic reductions in the effort and cost of forecasting; the provision of assistance to specialist forecasters; and increases in forecasting accuracy.
Metrics
8 Record Views
Details
- Title
- Comparative study of the predictive accuracy of multilayer perceptron networks versus simple recurrent networks for selecting forecasting methods
- Creators
- Murugan AnandarajanBay Arinze
- Publication Details
- The 1997 Annual Meeting of the Decision Sciences Institute. Part 1 (of 3); San Diego, CA; USA; 22-25 Nov. 1997, pp.373-375
- Conference
- The 1997 Annual Meeting of the Decision Sciences Institute (San Diego, California, United States, 22 Nov 1997 - 25 Nov 1997)
- Number of pages
- 1
- Resource Type
- Conference proceeding
- Language
- English
- Academic Unit
- Decision Sciences (and Management Information Systems)
- Identifiers
- 991019551782404721