A Novel Multi-criteria Inventory Classification Approach: Artificial Bee Colony Algorithm with VIKOR Method

Abstract

Abstract. ABC analysis is a well-established categorization technique based on the Pareto Principle which dispatches all the items into three predefined and ordered classes A, B and C, in order to derive the maximum benefit for the company. In this paper, we present a new approach for the ABC Multi-Criteria Inventory Classification problem based on the Artificial Bee Colony (ABC) algorithm with the Multi-Criteria Decision Making method namely VIKOR. The ABC algorithm tries to learn and optimize the criteria weights, which are then used as an input parameters by the method VIKOR. The MCDM method generates a ranking items and therefore an ABC classification. Each established classification is evaluated by an estimation function, which also represents the objective function. The results of our proposed approach were obtained from a widely used data set in the literature, and outperforms the existing classification models from the literature, by obtaining better inventory cost.

Group multiple criteria ABC inventory classification using TOPSIS approach extended by Gaussian interval type-2 fuzzy sets and optimization programs

“…Several approaches have applied arti cial intelligence techniques to the MCABCIC problem. Cherif and Ladhari [6] presented an integrated approach based on the arti cial bee colony algorithm and VIKOR method for MCABCIC where the arti cial bee colony algorithm was used to learn and optimize the criteria weights as the input parameters for VIKOR, which was then utilized for ranking items. Isen and Boran [7] generated a hybrid model including genetic algorithm, fuzzy c-means, and adaptive neuro-fuzzy inference system for inventory classi cation.…”