DESIGN OF MODIFIED RIPPER ALGORITHM TO PREDICT CUSTOMER CHURN

Abstract

Technologies such as data warehousing, data mining, and campaign management software have made Customer Relationship Management (CRM) a new area where firms can gain a competitive advantage. It is becoming common knowledge in business that retaining existing customers is an important strategy to survive in industry. Once identified, these customers can be targeted with proactive retention campaigns in a bid to retain them. These proactive marketing campaigns usually involve the offering of incentives to attract the customer into carrying on their service with the supplier. These incentives can be costly, so offering them to customers who have no intention to defect results in lost revenue. Also many predictive techniques do not provide significant time to make customer contact. This time restriction does not allow sufficient time for capturing those customers who are intending to leave. This research aims to develop methodologies for predicting customer churn in advance, while keeping misclassification rates to a minimum.