Combining both ensemble and dynamic classifier selection schemes for prediction of mobile internet subscribers

The recent trend of combining internet with cellular phone gives an important chance to mobile telecommunication industry. It is mainly due to the fact that the mobile internet service based on cellular phone is not only more profitable than usual calling service but also it creates new incomes. With this background, mobile telecommunication companies wish to predict the subscribers of mobile internet service from the existing cellular phone users. In this case classification models play important roles and the improvement of classification accuracy has significant target marketing effects due to its huge market size. One of the main efforts made to improve the classification accuracy is a combined classification. This paper proposes a new combined classifier based on both ensemble (bagging) and dynamic classifier selection schemes (DCS). The proposed method is applied to the call data of subscribers and its result confirms the superiority of our approach over bagging and DCS methods.