Recommending Stores for Shopping Mall Customers with RecStore

Abstract

Today, mobility is a key feature in the new generation of Internet, which provides a set of custom services through numerous terminals. Smartphones, for example, are a tendency and almost mandatory to anyone living in an urban and modern context. Most of the developed cities have at least one shopping mall full of mobile device users. These shopping malls provide a number of stores, and people tend to have difficult in finding what they really need. This paper proposes a solution called RecStore. RecStore is a recommendation model to assist customers in reaching what they consider relevant at malls. The recommendation model considers user activities, 330 stores, 30 users and 3 baseline models. The precision, recall and f-measure improved at rates of 118%, 76% and 95% respectively in comparison to the second best model of each metric. Additionally, a mobile application — called InMap — was implemented based on our model RecStore.