Track: Artificial Intelligence

Abstract

Retail shelf space is one of the most precious resources in retail chains. The proper product assortment is conducted by determining which product to be displayed to maximize the revenue. Moreover, deciding the location and the amount of shelf space assigned for each displayed product critically affects the overall performance of the retail chains. This study introduces a mathematical model to optimize the retail revenue by manipulating the above decisions while considering products’ cross-elasticity on the demand.  Unlike the majority of the previous studies, the space allocated to each product is considered as a continuous variable that has a lower bound of one product faces not as multiples of it. The resulting model, a NP-hard one, is solved using an adaptive meta-heuristic algorithm based on artificial bee colony (ABC). Numerical examples are used to illustrate the performance superiority of the proposed adaptive ABC over the basic one to achieve an optimum or a near optimal solution to the model.