Loyal to your city? A data mining analysis of a public service loyalty program

a r t i c l e i n f o Keywords: Knowledge discovery Data mining CRM Behavioral data Loyalty card Customer loyalty programs are largely present in the private sector and have been elaborately studied. Applications from the private sector have found resonance in a public setting, however, simply extrapolating research results is not acceptable, as their rationale inherently differs. This study focuses on data from a loyalty program issued by the city of Antwerp (Belgium). The aim of the loyalty card entails large citizen participation, however, an active user base of only 20 % is reached. Predictive techniques are employed to increase this number. Using spatial behavioral user information, a Naive Bayes classifier and a Support Vector Machine are used which result in models capable of predicting whether a user will actively use its card, whether a user will defect in the near future and which locations a user will visit. Also, a projection of spatial behavioral data onto even more fine-grained spatio-temporal data is performed. The results are promising: the best model achieves an AUC value of 92.5 %, 85.5 % and 88.12 % (averaged over five locations) for the predictions, respectively. Moreover, as behavior is modeled in more detail, better predictions are made. Two main contributions are made in this study. First, as a theoretical contribution, fine-grained behavioral data contributes to a more sound decision-making process. Second, as a practical contribution, the city of Antwerp can now make tailored strategic decisions to increase its active user base. Since the evolution from a product-centric to a customer-centric approach, managing customer relationships has become a necessity for organizations [1]. Customers need to be understood on a per-customer basis in terms of their needs, preferences and potential [2,3]. Maintaining close ties to customers may lead to a competitive advantage and to customer loyalty [4]. In order for organizations to initiate and maintain connections to their customers, Customer Relationship Management (CRM) systems are used. Data mining forms an integral part of these systems and provides insight into raw customer data [5]. Consequently, organizations can closely monitor their customers and anticipate accordingly through proactive marketing such as offering personalized incentives [5]. An important source for CRM data constitutes the output of loyalty programs and more specifically from loyalty cards [6]. Loyalty card data is typically characterized by a large sample of transactional data connected to the customers, for which also socio-demographic …