Telecom user loss prediction method and device based on user internet behaviours

Abstract

The invention provides a telecom user loss prediction method and device based on user internet behaviours. The method comprises the steps of: obtaining at least one internet behaviour data of a targetuser; evaluating the internet behaviour data, and determining an evaluation parameter corresponding to the internet behaviour of the target user; and, on the basis of the evaluation parameter, predicting whether the target user is a potential loss user or not, and predicting the loss probability of the target user. According to the telecom user loss prediction method and device based on the userinternet behaviours provided by the invention, on the basis of internet behaviours of users, subjective feelings and wishes of the users are comprehensively considered based on the statistics; therefore, potential loss users can be predicted in advance; furthermore, a user loss reason can be evaluated completely and accurately; the result is true and reliable; simultaneously, the user loss has periodicity; the potential loss users are predicted in advance; therefore, the users can be discovered in time, and retained by adoption of a corresponding marketing method; the pertinence is high; and the success rate is high.

Description

technical field [0001] The invention relates to the field of network technology, in particular to a method and device for predicting loss of telecommunication subscribers based on subscriber surfing behavior. Background technique [0002] With the rapid development of the mobile communication industry for a period of time, it is gradually entering a period of slow growth, and the number of registered users shows a dynamic growth trend, that is, while a large number of new users join the network, a large number of old users leave the network. Therefore, effective analysis of the reasons for user loss can attract potential users to join the network, increase the satisfaction of existing users, reduce the probability of user loss, thereby improving user consumption levels and fully occupying the market, which is the key to winning in the fierce market competition. [0003] The current user churn analysis is basically carried out by using data mining and other analysis methods, ...

AI Technical Summary

Problems solved by technology

[0005] The present invention provides a method and device for predicting the churn of telecommunication users based on users' online behaviors, so as to solve the problems in the prior art that the potential churn users cannot be predicted in advance and the reasons for user churn can be comprehensively and accurately evaluated

Images