. This article discusses the development of a recommendation system for the Siberian Logistics Company (SLC) aimed at optimizing the supply of food products to retail points. In the face of increasing competition, companies are forced to improve service quality and offer products that meet the needs of retail locations. The recommendation system, based on content filtering methods, analyzes real-time data on demand, assortment, and stock levels, providing personalized recommendations for sales representatives. The article describes the technical features of the system, the selection of tools and approaches, as well as the use of Python and Jupyter Notebook for development. The implementation of the system significantly accelerates data processing, improves the accuracy of recommendations, and enhances the company's adaptation to market changes. In the future, the system’s functionality can be expanded with the use of artificial intelligence and predictive analytics.