Pr. Philipoom et al., COST-BASED DUE-DATE ASSIGNMENT WITH THE USE OF CLASSICAL AND NEURAL-NETWORK APPROACHES, Naval research logistics, 44(1), 1997, pp. 21-46
Citations number
23
Categorie Soggetti
Operatione Research & Management Science","Operatione Research & Management Science","Engineering, Marine
Traditional methods of due-date assignment presented in the literature
and used in practice generally assume cost-of-earliness and cost-of-t
ardiness functions that may bear little resemblance to true costs. For
example, practitioners using ordinary least-squares (OLS) regression
implicitly minimize a quadratic cost function symmetric about the due
date, thereby assigning equal second-order costs to early completion a
nd tardy behavior. In this article the consequences of such assumption
s are pointed out, and a cost-based assignment scheme is suggested whe
reby the cost of early completion may differ in form and/or degree fro
m the cost of tardiness. Two classical approaches (OLS regression and
mathematical programming) as well as a neural-network methodology for
solving this problem are developed and compared on three hypothetical
shops using simulation techniques. It is found for the cases considere
d that: (a) implicitly ignoring cost-based assignments can be very cos
tly; (b) simpler regression-based rules cited in the literature are ve
ry poor cost performers; (c) if the earliness and tardiness cost funct
ions are both linear, linear programming and neural networks are the m
ethodologies of choice; and (d) if the form of the earliness cost func
tion differs from that of the tardiness cost function, neural networks
are statistically superior performers. Finally, it is noted that neur
al networks can be used for a wide range of cost functions, whereas th
e other methodologies are significantly more restricted. (C) 1997 John
Wiley & Sons, Inc.