A regression-based improvement to the multiple criteria ABC inventory classification analysis
- PDF / 315,638 Bytes
- 14 Pages / 439.37 x 666.142 pts Page_size
- 93 Downloads / 189 Views
A regression-based improvement to the multiple criteria ABC inventory classification analysis Giannis Karagiannis1 · Suzanna M. Paleologou2 Accepted: 9 September 2020 © Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract The aim of this paper is to propose a regression-based approach for obtaining a set of weights for multi-criteria ABC inventory analysis, which differ across classification criteria but are common across inventory items and follow a predetermined descending ordering scheme regarding the relative importance of classification criteria. The proposed alternative is based on the Inequality Constrained Least Squared model and is to be compared with the existing linear and non-linear programming models available in the literature. Keywords Multi-criteria analysis · ABC inventory · Regression methods
1 Introduction The ABC analysis is perhaps the most widely used method in inventory management aiming to classify items into three ordered classes: class A contains a relatively small number (5–10%) of the most important items, class B includes a larger number (20–30%) of items with moderate importance while the remaining (50–70%) items with relatively little importance belong to class C.1 Initially, the ABC analysis was based on a single classification criterion, namely the annual dollar usage, but soon it was recognized that a number of other criteria, such as inventory cost, lead time, and several others listed in Hu et al. (2018) Appendix B, may also be useful for obtaining a satisfactory classification of inventory items. Flore and Whybark (1986, 1987) are the first to consider the ABC analysis as a multi-criteria problem, where a score summarizing achievements across the considered criteria is used first to rank all items and then to classify them into three classes. Since then, several alternative approaches (accompanied with a large number of empirical studies)2 have been used to deal with the 1 Multi-criteria classification is part of spare parts management along with demand forecasting, inventory optimization and supply chain system simulation (see Hu et al. 2018). 2 Douissa and Jabeur (2020) in the most recent review of the subject surveyed 83 studies.
B
Suzanna M. Paleologou [email protected] Giannis Karagiannis [email protected]
1
Department of Economics, University of Macedonia, 156 Egnatia Str., Thessaloniki, Greece
2
Department of Economics, Aristotle University of Thessaloniki, 54124 Thessaloniki, Greece
123
Annals of Operations Research
multi-criteria ABC inventory classification problem, which according to Douissa and Jabeur (2020) can be grouped into four categories: (i) those using mathematical programming; (ii) those relying on artificial intelligence and meta-heuristics; (iii) those employing multi-criteria decision making techniques; and (iv) those based on hybrid methods. Our work in this paper is linked with the literature in the first category, where alternative linear programming models are used to estimate items’ score by means of a weighted ave
Data Loading...
