Telecommunication is very important as it serves various activities, services of electronic systems to transmit messages via physical cables, telephones, or cell phones. The two main factors that affect the growth of telecommunications are the rapid growth of modern technology and the market demand and its competition. These two factors in return, create new technologies and products, which open a series of options and offers to customers, in order to satisfy their needs and requirements. However, one crucial problem that commercial companies in general and telecommunication in particular, suffer from is a loss of valuable customers to competitors; this is called customer churn prediction. In this paper, the dynamic training technique is introduced. The dynamic training is used to improve the prediction of performance. This technique is based on two ANN network configurations to minimise the total error of the network to predict two different classes; names churn and non-customers.
展开▼
