Using Combined Model Approach for Churn Prediction in Telecommunication

Abstract

Abstract:To solve the prediction problem of hybrid data in users' consumption information of telecommunication, the paper use the fuzzy K-Prototypes (FKP) and support vector machine (SVM) combined model to improve the accuracy of users churn prediction. In the combined model, FKP is adopted to cluster hybrid large data volume effectively, and then the samples nearby cluster center in each cluster as the input of SVM to promote the prediction efficiency. As shown in the experience validation results, the proposed FKP-SVM combined model has excellent performance in predicting churn, due to reduce the training time of hybrid large-scale data set and save system resources.