Recognizing Residents and Tourists with Retail Data Using Shopping Profiles

Abstract

The huge quantity of personal data stored by service providers registering customers daily life enables the analysis of individual fingerprints characterizing the customers’ behavioral profiles. We propose a methodological framework for recognizing residents, tourists and occasional shoppers among the customers of a retail market chain. We employ our recognition framework on a real massive dataset containing the shopping transactions of more than one million of customers, and we identify representative temporal shopping profiles for residents, tourists and occasional customers. Our experiments show that even though residents are about 33% of the customers they are responsible for more than 90% of the expenditure. We statistically validate the number of residents and tourists with national official statistics enabling in this way the adoption of our recognition framework for the development of novel services and analysis.