Integrating data mining and AHP for life insurance product recommendation

Abstract

Product recommendation is critical in attracting customers particularly in life insurance where the company has multiple options for the customer. Accordingly, improving the quality of a recommendation to fulfill customers' needs is important in competitive environments. Although various recommendation systems have been proposed, few have addressed the lifetime value of a customer to a firm. We developed a two-stage product recommendation methodology that combines data mining techniques and analytic hierarchy process (AHP) for decision-making. Firstly clustering technique was applied to group customers according to the age and income because these two are very important in deciding insurance product. Secondly the AHP was then applied to each cluster to determine the relative weights of various variables in evaluating the suitable product for them. © 2011 Springer-Verlag.