Abnormal Phone Analysis Based on Learning to Rank and Ensemble Learning in Environment of Telecom Big Data

With the rapid development of Telecom era, the number of telecom users has increased dramatically. User phone have been widely recognized as user identities and are registered in a large number of Internet applications. Due to the leakage of user information, a series of social problems have arisen. Abnormal telephone has become a social problem to be solved. Current methods are mostly passive detection methods, and some of them are extremely expensive and do not meet the requirements of practical application. Our current situation of lack of effective control measures and active detection methods for abnormal phones. Based on the existing telecommunication big data, an abnormal phone active detection method is designed based on learning to rank and ensemble learning algorithm. The experimental results on the real dataset show that the proposed method has higher accuracy than the experimental results obtained by a single learning algorithm.