Artificial Neural Networks-Based Forecasting: An Attractive Option for Just-in-Time Systems

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.

[1]  Halbert White,et al.  Connectionist nonparametric regression: Multilayer feedforward networks can learn arbitrary mappings , 1990, Neural Networks.

[2]  José M. Castro,et al.  Identifying the Best Compromises between Multiple Performance Measures in Injection molding (im) using Data envelopment Analysis (DEA) , 2003, Trans. SDPS.

[3]  Kalyanmoy Deb,et al.  Multi-objective optimization using evolutionary algorithms , 2001, Wiley-Interscience series in systems and optimization.

[4]  C. Hillermeier Nonlinear Multiobjective Optimization: A Generalized Homotopy Approach , 2001 .

[5]  Mauricio Cabrera-Ríos,et al.  Statistical Characterization and Optimization of Artificial Neural Networks in Time Series Forecasting: The One-Period Forecast Case , 2006, Computación y Sistemas.

[6]  H. Brian Hwarng,et al.  Insights into neural-network forecasting of time series corresponding to ARMA(p,q) structures , 2001 .

[7]  Mauricio Cabrera Rios,et al.  Modelling and simulation in reactive polymer processing , 2004 .

[8]  Jay L. Devore,et al.  Probability and statistics for engineering and the sciences , 1982 .

[9]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[10]  Marcelo C. Medeiros,et al.  What are the effects of forecasting linear time series with neural networks , 2001 .

[11]  Robert Fildes,et al.  The accuracy of a procedural approach to specifying feedforward neural networks for forecasting , 2005, Comput. Oper. Res..

[12]  Michael Y. Hu,et al.  A simulation study of artificial neural networks for nonlinear time-series forecasting , 2001, Comput. Oper. Res..

[13]  Claus Hillermeier,et al.  Nonlinear Multiobjective Optimization , 2001 .

[14]  Christopher M. Bishop,et al.  Neural networks for pattern recognition , 1995 .

[15]  G. Peter Zhang Neural Networks in Business Forecasting , 2003 .

[16]  Michael Y. Hu,et al.  Forecasting with artificial neural networks: The state of the art , 1997 .

[17]  M. Cabrera-Rios,,et al.  Multiple Quality Criteria Optimization in Reactive In-Mold Coating (IMC) with a Data Envelopment Analysis approach , 2002 .

[18]  Martin T. Hagan,et al.  Neural network design , 1995 .

[19]  Mauricio Cabrera-Ríos,,et al.  MULTIPLE QUALITY CRITERIA OPTIMIZATION IN REACTIVE IN-MOLD COATING WITH A DATA ENVELOPMENT ANALYSIS APPROACH II: A CASE WITH MORE THAN THREE PERFORMANCE MEASURES , 2004 .

[20]  J. V. Hansen,et al.  Forecasting and recombining time-series components by using neural networks , 2003, J. Oper. Res. Soc..