Semnan University Press Journal of Modeling in Engineering 2008-4854 23 82 2025 09 23 Storage Location Assignment Problem using Data Mining Approach (Case Study: Mobarakeh Steel Company) Storage Location Assignment Problem using Data Mining Approach (Case Study: Mobarakeh Steel Company) 23 35 9703 10.22075/jme.2024.33295.2624 FA Hossein Raesi Dezaki Department of Industrial and Systems Engineering, Isfahan University of Technology, Isfahan, Iran Gholam Ali Reisi Ardali Department of Industrial and Systems Engineering, Isfahan University of Technology, Isfahan, Iran Journal Article 2024 02 15 One of the influential factors in manufacturing industries to maintain competitiveness and meet customer expectations is optimizing warehouse management, including the allocation of products to storage locations within the warehouse. Proper arrangement can reduce order picking time and increase responsiveness to orders in the warehouse. This research focuses on the topic of inventory management using data-driven tools. In this study, one of the warehouses of Mobarakeh Steel in Isfahan was considered as a case study, and the process of allocating products to shelves was carried out in two stages. In the first stage, products were divided into four clusters using the k-means algorithm. To improve the quality of clustering, two steps were taken: "a pre-algorithm that selects initial k-means points with greater dispersion" and "a genetic algorithm that eliminates local optima in cluster solutions." In the second stage, the location of each cluster in the warehouse was determined based on experts experience. Subsequently, based on a preference criterion, products in each cluster were assigned to different shelves. Several orders were randomly selected, and the total distances of the ordered products were calculated. The results show that the proposed model can reduce the total distances of products in orders in the warehouse by an average of 15 percent. One of the influential factors in manufacturing industries to maintain competitiveness and meet customer expectations is optimizing warehouse management, including the allocation of products to storage locations within the warehouse. Proper arrangement can reduce order picking time and increase responsiveness to orders in the warehouse. This research focuses on the topic of inventory management using data-driven tools. In this study, one of the warehouses of Mobarakeh Steel in Isfahan was considered as a case study, and the process of allocating products to shelves was carried out in two stages. In the first stage, products were divided into four clusters using the k-means algorithm. To improve the quality of clustering, two steps were taken: "a pre-algorithm that selects initial k-means points with greater dispersion" and "a genetic algorithm that eliminates local optima in cluster solutions." In the second stage, the location of each cluster in the warehouse was determined based on experts experience. Subsequently, based on a preference criterion, products in each cluster were assigned to different shelves. Several orders were randomly selected, and the total distances of the ordered products were calculated. The results show that the proposed model can reduce the total distances of products in orders in the warehouse by an average of 15 percent. https://modelling.semnan.ac.ir/article_9703_fffe95693728f06947f654ba614feeca.pdf