INTELLIGENT SUPERMARKET MARKETING THROUGH RFID-ENABLED IOT AND MACHINE LEARNING

Abstract

The rapid evolution of retail technologies has transformed the way supermarkets manage customer engagement and marketing strategies. This study proposes an intelligent supermarket marketing framework that integrates Radio Frequency Identification (RFID) and Internet of Things (IoT) technologies with machine learning for customer behavior analysis. RFID tags and IoT sensors are employed to capture real-time customer movement, product interactions, and purchase histories within the supermarket environment. The collected data is processed and analyzed using multiple machine learning algorithms, including k-means clustering, Decision Tree (DT), and Support Vector Machine (SVM), to classify customer activities such as browsing, purchasing, and ignoring products. Comparative performance analysis shows that these models effectively identify customer behavior patterns, supporting personalized marketing strategies, optimized product placements, and improved inventory management. Experimental simulations demonstrate that the proposed system achieves high predictive accuracy, enabling supermarkets to design data-driven campaigns, increase conversion rates, and enhance overall sales efficiency. The combination of RFID-enabled IoT infrastructure with supervised machine learning provides a scalable, cost-effective, and intelligent approach to modern retail marketing. This research highlights the potential of integrating classification-based analytics into supermarket ecosystems to foster improved customer experience and strategic decision-making.