Model of Appling Data Mining Techniques in identification, segmentation and Analysis of Customers Behaviour of Electronic Banking Services


1 MSc. In Information Technology Management, University of Shiraz, Shiraz, Iran

2 Department of Information Technology Management, Science and Research Branch, Islamic Azad University, Tehran, Iran


Banks need to identify and analyze the behavior of their customers in order to present electorinc services to them. In high volume customers' data set, data mining techniques can help to gain hidden knowledge for supporting marketing decisions. The main problem is how using data mining and RFM analysis model in identification and analysis of customers' behavior in order to segment and classify and select groups of valuable customers. The proposed model in this paper is based on CRISP – DM standard in data mining and in this model, after data preparation and preprocessing, two approaches are presented. 1. Customers segmentation via clustering and then, calculate customer value in clusters and ranking them for finding valuable clusters. 2. Scoring and determine customer value as target attribute in construction of classification models of customers value. Demographic and transactional data set are used to train and test of the proposed model. Results shows using the proposed model can identify and analyze customers with respect to their behaviors and segment and classify them until supporting and promoting marketing decisions can be done.