Customer-Churn Research Based on Customer Segmentation

This article explores the unique features of the customer relationship management (CRM) system in Telecom industry and presents a customer-churn model based on customer segmentation. First, the improved Fuzzy C-means clustering algorithm is used to segment customer and conclude high value customer group characteristics. Second, using the history data and SAS Enterprise Miner builds a prediction model of customer-churn based on SAS data mining technology. Last but not least, the result of customer segmentation is applied to customer-churn model and gotten accuracy list of lost customer. Experiment proves that this method can obtain a satisfactory result of customer-churn.