Customer churn is the customer’s decision to terminate the relationship with a provider. This decision can be very onerous to the business financial performance. As such, an a priori knowledge about the probability (risk) of a given customer to cancel the relationship with the firm in the next period is a valuable tool that allows firms to take preventive measures to avoid the defection of potentially profitable customers. This study aims to understand and predict customer lifetime in a contractual setting in order to improve the practice of customer portfolio management. A duration model is developed to understand and predict the residential customer churn in the fixed telecommunications industry in Portugal. The model is developed by using large-scale data from an internal database of a Portuguese company which presents bundled offers of ADSL, fixed line telephone, pay-TV and home-video. The model is estimated with a large number of covariates, which includes customer’s basic information, demographics, churn flag, customer historical information about usage, billing, subscription, credit, and other

--

Duration models,Survival analysis,Customer defection,Customer retention,Customer management