Recommender System Using Machine Learning and BLE Beacons

Abstract

AbstractNowadays, Recommender system is present in our daily activities, people need the help of computer systems and machine learning to simplify their regular activities. Grocery shopping is an everyday essential task of people’s life so the retailers must exploit the advancement of technology to know their customers better and to improve their marketing strategies. This paper aims to apply machine learning algorithms to the development of a recommender system capable of preparing personalized grocery shopping lists. The proposed framework exploits K-means algorithm and Apriori association rules to understand the customer’s behavior. The K-means algorithm was used to identify groups of customers based on transactional data and movements of customers; it also divides customers into ten groups of customers. Apriori association rule was used to characterize the groups of customers by creating customer profiles. The analysis of customer behavior is helpful for the decision marketing managers to send the right promotion to the right consumer at the right time.KeywordsDataminingRecommendation systemsLocation-based servicesTrajectory-ticketK-means algorithmApriori association rule