Journal article
A comparative study of multilayer perceptron topologies for the selection of forecasting methods
The Journal of computer information systems, Vol.39(2)
01 Dec 1998
Featured in Collection : UN Sustainable Development Goals @ Drexel
Abstract
Forecasting is an important and necessary activity for all types of organizations. Selecting the right forecasting method is a complex and time-consuming task. Nevertheless, the imperative to plan requires that organizations devote considerable resources to selecting appropriate forecasting methods to better anticipate future demand and determine resource allocation This research describes the use of a Neural network (specifically a multilayer perceptron) to select the most accurate forecasting method for any given time series. In addition, this paper examines the effect of increasing the number of hidden layers on the network's selection accuracy. Econometric time series data sets were used to train and test the neural networks. The results of this experiment, which appear promising, are presented together with guidelines for their practical application. Potential benefits include dramatic reductions in the effort and cost of forecasting, the provision of assistance to specialist forecasters and, of course, a substantial increase in forecasting accuracy.
Metrics
1 Record Views
Details
- Title
- A comparative study of multilayer perceptron topologies for the selection of forecasting methods
- Creators
- M AnandarajanB Arinze
- Publication Details
- The Journal of computer information systems, Vol.39(2)
- Publisher
- INT ASSOC COMPUTER INFO SYSTEM
- Number of pages
- 6
- Resource Type
- Journal article
- Language
- English
- Academic Unit
- Decision Sciences (and Management Information Systems)
- Identifiers
- 991019170561204721
UN Sustainable Development Goals (SDGs)
This output has contributed to the advancement of the following goals:
InCites Highlights
These are selected metrics from InCites Benchmarking & Analytics tool, related to this output
- Collaboration types
- Domestic collaboration
- Web of Science research areas
- Computer Science, Information Systems