Abstract

The problem of products missing from the shelf is a major one in the grocery retail sector, as it leads to lost sales and decreased consumer loyalty. Yet, the possibilities for detecting and measuring an out-of-shelf situation are limited, mainly conducted via a physical shelf check. The existence of an automatic method for detecting the products that are not on the shelf based on sales data would thus be valuable, offering an accurate view of the shelf availability both to retailer and the product suppliers. In this paper, an information system is proposed in order to detect (thus measure) products that are not on the shelf. The proposed method is a rule-based information system as iteratively developed by the utilization of Machine Learning techniques. Through the comparison of the proposed method with an existing approach called OOS Index, we draw some results regarding the detection capabilities each method has. Results up to now present that rules related with detection of the out-of-shelf products are characterized by acceptable levels of predictive accuracy and problem support.