Mining Telecommunication Churn Behaviors And Developing Retention Strategies Based On Memorized Clustering

With the increasingly fierce market competition, Customer churn has emerged as a critical issue for Customer Relationship Management and customer retention in the telecommunications industry. Thus churn prediction is necessary and valuable to retain the customers and reduce the losses. Various supervised learning techniques have been used to study customer churn. However, research on the use of unsupervised learning techniques for prediction of churn is limited. Clustering is one of the unsupervised learning techniques, by using Clustering analysis, customers who have similar behavioral patterns(that can be described by multiple attributes) can be grouped together. So we can characterize the features of a specific customer group.Based on the discussion above, this study aimed at identifying churners by employing data mining techniques and adopting knowledge discovery process. To this end, a hybrid approach consisting of preprocessing, clustering, and classification phases was applied, and appropriate tools were employed commensurate to each phase. Specially, in the clustering phase SOM and K-means were combined, and in the classification phase decision tree(C4.5), neural networks, and support vector machines as single classifiers and bagging, boosting, stacking, majority voting as ensembles were examined. In addition to using clustering to segment customers, it was also possible – by defining new features – to maintain the results of clustering phase for the classification phase. We call this method memorized clustering, and this, in turn, contributed to better classification results. A real telecom dataset was applied to demonstrate the effectiveness of the proposed method. The efficient use of synergy among these techniques significantly increased prediction accuracy. The performance of all single and ensemble classifiers is evaluated based on various metrics and compared by statistical tests. The results showed that support vector machines among single classifiers and bagging trees among all classifiers have the best performance in terms of various metrics. Further, in order to improve the usefulness of the classification results in the real world, a set of simple churn marketing programs is presented and discussed. The research findings show that the proposed model has a high accuracy, and the resulting outcomes are significant both theoretically and practically.