A Hyper-Personalized Product Recommendation System Focused on Customer Segmentation: An Application in the Fashion Retail Industry

Providing the right products, at place and time, according to their customer’s preferences, is a problem-seeking solution, especially for companies operating in retail industry. This study presents an integrated product RS that combines various data mining techniques with this motivation. The proposed approach consists of following steps: (1) customer segmentation; (2) adding location dimension determining association rules; (3) creation recommendations. We used RFM technique segmentation k-means clustering algorithm create segments customer-based values. Then, Apriori algorithm, one rule algorithms, accurate rules. In way, cluster-based rules are created. Finally, recommendations presented rule-based heuristic algorithm. first system considers customers’ demographic fashion industry literature. Furthermore, information as parameter time phase RS. systematic aimed producing hyper-personalized customers. implemented on real-world e-commerce compared current RSs well-known metrics average sales information. results show provides better