Fashion retail recommendation system by multiple clustering

Fashion retail has a large popularity and relevance, allowing customers to buy anytime finding the best offers and providing nice experiences in the shops. Consequently, Customer Relationship Management solutions have been enhanced by Information and Communication Technologies to better understand the behaviour and requirements of customers, engaging and influencing them to improve their buying experience, as well as increasing the retailers' profitability. Current solutions on marketing provide a too general approach, based on most popular or most purchased items, losing the focus on the customer centricity. In this paper, a recommendation system for fashion retail shops is proposed, based on a multi clustering approach of items and users' profiles in online and on physical stores. The proposed solution relies on association rules mining techniques, allowing to predict the purchase behavior of newly acquired customers, thus solving the cold start problems which is typical of current state of the art systems. The presented work has been developed in the context of the Feedback project founded by Regione Toscana, and it has been conducted on real retail company Tessilform, Patrizia Pepe mark. The recommendation system has been validated in store, as well as online.