A Hybrid Intelligent System for Personalized Recommendations in Offline Retail

Abstract

In offline retail settings, there are two major challenges: improving the customer experience through personalized product recommendations and optimizing inventory management through accurate sales forecasting. Conventional recommendation systems assist customers in selecting goods based on personal preferences, similar user behavior, and popularity trends, while forecasting systems help managers predict future sales and optimize inventory levels. However, existing approaches face limitations in offline retail environments due to the scarcity of explicit feedback and the complexity of in-store interactions. To address these limitations, this paper introduces a hybrid intelligent system that combines multiple recommendation paradigms with predictive modeling techniques. By leveraging Recurrent Neural Networks and data-driven statistical models, the system improves both recommendation accuracy and demand forecasting reliability compared to traditional approaches. The effectiveness of the proposed system has been thoroughly evaluated using standard metrics such as Mean Reciprocal Rank at K (MRR@K) and Hit Rate at K (HR@K). Experimental results confirm the effectiveness of the proposed approach in balancing personalization and accuracy, offering significant benefits in offline retail environments.