Mining Changes In Bank Customer Behavior Using Clustering Techniques

Customer Relationship Management has generated an increasing interest among academics and practitioners over the past few years. This is due to competitive marketing environment, advancement in technology and changing behavior of customers which are difficult to predict. CRM is a new marketing method that allows banks to shift their business focus from product centric to customer centric. This is attained by using customer segmentation scheme that divides customers into distinct, meaningful and homogenous subgroups based on various attributes and characteristics. Customer segmentation is one of the major core functions of Customer Relationship Management (CRM). There are several segmentation schemes like by value, socio-demographic, loyalty, needs/attitudinal and behavior. This thesis focuses on behavioral segmentation.Despite of numerous studies that have provided important insights into the CRM strategy, the understanding of this topic of growing interest and importance still remains deficient. Therefore, the objective of this thesis is to provide a comprehensive framework intended to guide research efforts focusing on Customer Relationship Management as well as to aid practitioners and marketers in their quest to achieve CRM success using data mining methods for customer segmentation. The framework builds on the literature from CRM and integrated data mining methodologies and provides a systematic approach as to how CRM in customer segmentation should be integrated into the firm’s overall marketing strategy. To evaluate the CRM framework for customer segmentation in bank, a case study of bank credit cards is used for customer behavioral segmentation that segmented costumers based on their purchasing habits especially the mix of products that they tend to buy. Two-step clustering was used to segment customers into groups of five segments. These five segments were profiled using CHAID Decision tree which gives a better model and accuracy of74.8%.