Customer Churn's Analysis And Application Of Telecom

With the development of telecom market accelerating, competition among telecommunication operation companies became more severe. the emphases of the clients relations management is turned from the basic function of the business-accepted, the business, the suit and so on to the control which the customer drains. According to investigates, the cost which the enterprise spends in attracting a new customer is about five to ten times than in maintaining an existing customer. Therefore, the telecommunication operation companies are urgent to figure out how to maintain the existing customer. In order to do it, the telecommunication operation companies need to predict the possibility of the client-draining before clients give up their services. So some corresponding market strategy may be taken. in order to meet the need of the telecommunication operation companies ,The model of client churn in the paper is introduced and provides them a decision support system , which help them find out clients who have high possibility of churn from the massive clients.The paper first makes a definition of client churn, according to the reason which clients give up the service, clients are classified differently. After analysing the datum of the different classification and questionnaire of a mount of clients, some common characteristic is obtained. Such as: Age, time in line, the month amount of consumption, proportion of the host call, frequency of fall and frequency of the call to the center of clients service and so on. The input of the RBF input is this 20 factors, the RBF study algorithm and the effect which the center, the weight and width of RBF neural network affects the ability of generalization and approximation is introduced in detail, the width of RBF affects the generalization of the neural networks directly where large width leads to inaccuracy while on the contrary, small width harms the generalization. Therefore the weight and the center of RBF is getten by the nearest beighbor-clustering algorithm,when selecting the width of RBF ,we give up the way which the width is decided by experience, The Chaos Search Algorithm was adopted to optimize the spread of RBF. From the evaluation of on model with actual data, it demonstrates that such a predictive model based on the optimization of the RBF width can provide a comparative more accurate prediction of clients churn and has its own practicability and validity.