Advertisement
Published in:
2012 | OriginalPaper | Chapter
11. Artificial Neural Networks-Based Forecasting: An Attractive Option for Just-in-Time Systems
Authors : Mauricio Cabrera-Ríos, María Angélica Salazar-Aguilar, María Guadalupe Villarreal-Marroquín, Ángela Patricia Anaya Salazar
Published in: Just-in-Time Systems
Publisher: Springer New York
Activate our intelligent search to find suitable subject content or patents.
Select sections of text to find matching patents with Artificial Intelligence. powered by
Select sections of text to find additional relevant content using AI-assisted search. powered by
Abstract
Just-in-time (JIT) systems focus on lead-time reduction and equalization to make them respond rapidly to changes in demand. Lead-time variability in real life production, however, does affect the performance of JIT systems. This makes demand forecasting an important task to ponder. In this chapter, the use of artificial neural networks (ANNs) is advocated as an attractive approach to forecast demand for JIT systems. ANNs’ capabilities to accommodate nonlinear dependencies and to generate forecasts for multiple periods ahead are among the most important reasons to consider for their adoption. A general method to build ANNs for time series prediction is presented aiming to circumvent some of the perceived difficulties associated to these models. Two case studies are also provided to illustrate the intended use.