Application of neural network for customer lifetime value prediction : a case study in a telecommunication business

Abstract

This thesis studies the way to treat customer relationship in the telecommunications industry. Therefore, how a person measure and manage customer lifetime value (CLV) for determining the likely future profit from the customer is very important because the customers are always looking for better and cheaper products and services. The CLV not only combines with the churn management but also considers the cross-selling and up-selling to allure customer. Earning, not just buying, customers’ loyalty is now mandatory. The method to analyze and predict customer lifetime value (CLV) using Artificial neural network (ANN) is proposed here. In this study, multi-layer perceptron (MLP) network with Levenberg-Marquardt algorithm is used to predict the CLV. Additionally, the performance of neural network is compared with decision tree using C4.5 algorithm. The accuracy of the prediction value of the neural network is 96.5%. The experiment result illustrated that the neural network model has a higher performance than the decision tree