摘要
The penetration of mobile phones is nearly saturated in both developing and developed regions. In such a circumstance, how to prevent subscriber churn has become an important issue for today＇s telecom operators, as the cost to acquire a new subscriber is much higher than that to retain an existing subscriber. In this paper, we propose to leverage the power of big data to mitigate the problem of subscriber churn and enhance the service quality of telecom operators. As the information hub, telecom operators have accumulated a huge volume of valuable data on subscriber behaviors, service usage, and network operations. To enable efficient big data processing, we first build a dedicated distributed cloud infrastructure that integrates both online and offline processing capabilities. Second, we develop a complete churn analysis model based on deep data mining techniques, and utilize inter-subscriber influence to improve prediction accuracy. Finally, we use real datasets obtained from a large telecom operator in China to verify the accuracy of our churn analysis models. The dataset contains the information of over 3.5 million subscribers, which generate over 600 million call detail records （CDRs） per month. The empirical results demonstrate that our proposed method can achieve around 90% accuracy for T ＋ 1 testing periods and identify subscribers with high negative influence successfully.
The penetration of mobile phones is nearly saturated in both developing and developed regions. In such a circumstance, how to prevent subscriber churn has become an important issue for today＇s telecom operators, as the cost to acquire a new subscriber is much higher than that to retain an existing subscriber. In this paper, we propose to leverage the power of big data to mitigate the problem of subscriber churn and enhance the service quality of telecom operators. As the information hub, telecom operators have accumulated a huge volume of valuable data on subscriber behaviors, service usage, and network operations. To enable efficient big data processing, we first build a dedicated distributed cloud infrastructure that integrates both online and offline processing capabilities. Second, we develop a complete churn analysis model based on deep data mining techniques, and utilize inter-subscriber influence to improve prediction accuracy. Finally, we use real datasets obtained from a large telecom operator in China to verify the accuracy of our churn analysis models. The dataset contains the information of over 3.5 million subscribers, which generate over 600 million call detail records （CDRs） per month. The empirical results demonstrate that our proposed method can achieve around 90% accuracy for T ＋ 1 testing periods and identify subscribers with high negative influence successfully.
基金
This work was supported in part by the National Natural Science Foundation of China under Grant Nos. 61272397, 61472454, and 61572538, and the Guangdong Natural Science Funds for Distinguished Young Scholar under Grant No. S20120011187.
