Personalized Shopping Experience in Retail through Internet of Things-enabled Indoor Positioning and Real-time Product Recommendations

摘要

The competitive pressures of e-shopping are compelling the retail industry to invest in more personalized and interactive shop to enhance networking experiences of customers. Customized recommendations, ease of navigation, and hassle-free shopping experience are emerging trends. Conversely, the conventional bricks-and-mortar stores find it difficult to offer these experiences due to limited physical tracking capabilities and generic marketing, which decreases customer engagement and cross-selling opportunities. To resolve this operational gap, this study proposes a smart store framework that integrates Internet of Things (IoT)-enabled indoor positioning system with real-time, data-driven product recommendations. This system uses the ultra-wideband (UWB) sensors and mobile tags placed in a retail space in order to track customer movement and gather accurate location-based behavioural data. The spatial data is then mined through the usage of association rule mining to extract highly confident purchasing patterns and generate personalized product recommendations based on essential yardsticks like support, confidence as well as lift. The paper presents a case study based on a real time supermarket scenario to show that the algorithm can effectively find the best complementary products in order to extract high and useful cross selling rules on the daily use products. Moreover, incorporating augmented reality (AR) technology offers proximity-based visualization that significantly enhances in-store navigation for the end user. In conclusion, a solution designed to improve customer convenience and satisfaction and enables retail management to utilize data and a scalable solution to optimize physical store layouts and implement highly targeted promotions to build long-term customer loyalty in a digital world.