International Journal on Recent and Innovation Trends in Computing and Communication ISSN: 2321-8169 Volume: 1 Issue: 9 720 – 725 ______________________________________________________________________________ 720 IJRITCC | September 2013, Available @ http://www.ijritcc.org ______________________________________________________________________________ Data Mining as a tool to Predict the Churn Behaviour among Indian bank customers Manjit Kaur Department of Computer Scienc Punjabi University Patiala, India manjit8718@gmail.com Dr. Kawaljeet Singh University Computer Centre Punjabi University Patiala, India singhkawaljeet@rediff.com Dr. Neeraj Sharma Department of Computer Scienc Punjabi University Patiala, India sharmaneeraj@hotmail.com Abstract — The socio economic growth of the country is mainly dependent on the services sector. The financial sector is one of these services sector. Data mining is evolving into a strategically important dimension for many business organizations including banking sector. The churn problem in banking sector can be resolved using data mining techniques. The customer churn is a common measure of lost customers. By minimizing customer churn a company can maximize its profits. Companies have recognized that existing customers are most valuable assets. Customer relationship management (CRM) can be defined as the process of acquiring, retaining and growing profitable customer which requires a clear focus on service attributes that represent value to the customer and creates loyalty. Customer retention is critical for a good marketing and a customer relationship management strategy. The prevention of customer churn through customer retention is a core issue of Customer relationship management. Predictive data mining techniques are useful to convert the meaningful data into knowledge. In this analysis the data has been analyzed using probabilistic data mining algorithm Naive Bayes, the decision trees algorithm (J48) and the support vector machines(SMO). Index Terms — customer churn; banking sector; predictive data mining; CRM ________________________________________________________*****_____________________________________________________ I. INTRODUCTION Classification of the services sector by Central Statistical Organization (CSO) consists of four broad categories, first is ―trade, hotels and restaurants‖, second is ―transport, storage and communication‖, third is ―financing, insurance, real estate and business services‖ and the fourth is ―community, social and personal services‖ [10]. In Yojna, September 2011 issue, the services sector has been highlighted as the lifeline for the socio economic growth of a country. It is today the largest and fastest growing sector globally contributing more to the global output and employing more people than any other sector. Financial services sector is one of these sectors and data mining assists many kinds of analysis work in this area such as:  Financial product cross-selling  Market segment analysis  Fraud detection  Customer churn analysis Customer Retention is an increasingly pressing issue in today's ever- competitive commercial arena. Churn is defined as the propensity of a customer to stop doing business with an organization and subsequently moving to some other company in a given time period. The customer churn is a common measure of lost customers. Customer retention rate has a strong impact on the customer lifetime value, and understanding the true value of a possible customer churn will help the company in its customer relationship management (CRM). The subject of customer retention, loyalty, and churn is receiving attention in many industries. This is important in the customer lifetime value context. A company will have a sense of how much is really being lost because of the customer churn and the scale of the efforts that would be appropriate for retention campaign. The mass marketing approach cannot succeed in the diversity of consumer business today. Customer value analysis along with customer churn predictions will help marketing programs target more specific groups of customers. Personal retail banking sector is characterized by customers who stays with a company very long time. Customers usually give their financial business to one company and they won’t switch the provider of their financial help very often. In the company’s perspective this produces a stable environment for the customer relationship management. Although the continuous relationships with the customers the potential loss of revenue because of customer churn in this case can be huge. Data mining can be used to maintain customer relationship management. Various techniques are available to analyze and infer customer behavior in future using predictive data mining.