Multi Criteria ABC analysis using artificial – intelligence - based classification techniques – case study of a pharmaceutical company

ABC analysis is a popular and effective method used to classify inventory items into specific categories that can be managed and controlled separately. In traditional ABC analysis the inventory items are categorized in to A ,B and C classes based on the annual dollar usage. The annual dollar usage is determined as the product of unit cost of each item and its annual demand. The items are arranged in the descending order of annual dollar usage. In traditional ABC analysis annual demand and Unit cost are the only criteria for classification. Researchers have been developing multi – criteria ABC classification models to include criteria such as criticality, Lead time and ordering cost etc. Several classification methods have been proposed in the literature like Analytical Hierarchy process (AHP), Data Envelopment analysis (DEA) and TOPSIS, etc. In this paper the authors have applied artificial-intelligence –based classification methods for the inventory classification of a pharmaceutical manufacturing company. The AI methods proposed in this paper are Back-propagation (BP) artificial neural network, Support Vector Machines (SVM), K-Nearest neighbor and Multiple Discriminant Analysis (MDA). Out of the above methods SVM enables higher classification accuracy than the others. This finding suggests the possibility of implementing AI – based techniques for multi-criteria ABC analysis in enterprise resource planning (ERP) systems