Title: Selecting forecasting model parameters in Material Requirement Planning systems

Authors: Fujun Lai, Xiande Zhao, Tien-sheng Lee

Addresses: School of Accounting and Management Information Systems, College of Business, University of Southern Mississippi – Gulf Coast Long Beach, MS 39560, USA. ' Department of Decision Sciences and Information Systems, The Chinese University of Hong Kong, Satin, N.T., Hong Kong. ' Department of Decision Sciences and Information Systems, The Chinese University of Hong Kong, Satin, N.T., Hong Kong

Abstract: This paper investigates how the choice of parameters for forecasting models influences the performance of MRP systems. The results of the study show that the error measures, which are used to estimate forecasting parameters, have a significant effect on the system performance. Minimising Mean Absolute Deviation (MAD) and Mean Square Error (MSE) in choosing the forecasting model parameters will result in total cost that is much closer to the minimum cost than minimising the mean error (Bias). While operating parameters such as Freezing Proportion (FP) and Cost Structure (CS) do significantly influence the relationship between total cost and the error measures that are used to estimate forecasting model parameters, both MAD and MSE are better than Bias under all conditions. The use of Safety Stock (SS) does not influence the conclusion.

Keywords: forecasting models; simulation; material requirements planning; MRP; master production scheduling; MPS; internet; enterprise management.

DOI: 10.1504/IJIEM.2006.011044

International Journal of Internet and Enterprise Management, 2006 Vol.4 No.4, pp.331 - 354

Published online: 05 Oct 2006 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article