ABC inventory classification via linear discriminant analysis and ranking methods

ABC inventory classification is one of the most frequently used approaches in inventory planning and control. Sorting of inventory items into group categories has traditionally been facilitated by means of their relative value. During recent years, a number of attempts have been made to classify items by several criteria simultaneously, but none of them use statistical tools to evaluate the classification quality. This paper proposes to use linear discriminant analysis (LDA) and data envelopment analysis (DEA) in the context of ABC inventory classification. A numerical case study illustrates the applicability of the procedure. This is, to the best of our knowledge, the first work that uses LDA for ABC inventory classification.