Abstract
ABC analysis is an inventory management technique used to classify inventory items into three predefined and ordered categories A, B and C: Category A contains items with the highest impact for the company, while the category C contains items with the lowest impact. The aim of this classification technique is to keep related inventory costs under control. According to the ABC analysis, the classification of items into categories is based on their weighted scores. The score of each item is the result of an aggregation function that combines the item evaluations on the different criteria and the criteria weights. In ABC literature many classification models - issued from different fields such as Artificial Intelligence (AI), Mathematical Programming (MP) and Multi Criteria Decision Making (MCDM) - are proposed to infer the criteria weights. This paper proposes two classification models based on Genetic Algorithm (GA) to infer the criteria weights. The two classifications of items obtained by these models optimize respectively the two following objective functions: The Total Relevant Cost (TRC to be minimized) and the Inventory Turnover Ratio (ITR to be maximized). To estimate the performance of the proposed classification models, a benchmark data set of 47 items consumed in a Hospital Respiratory Therapy Unit (HRTU) is used.