Evaluation of the quality of functioning of a telecommunications company based on Data Mining technology

Abstract

The paper presents an approach to assessing the quality of a telecommunications company, which can be used to predict the churn of subscribers from a telecom operator. The originality of the approach lies in the use of such mathematical methods that make it possible to determine the main set of parameters due to which specific subscribers are inclined to change their mobile operator. The approach is based on data mining, namely the method of cluster analysis, which most fully allows assessing the quality of telecommunications companies functioning. Mathematical modeling of predicting customer churn using methods of association rules, decision trees and bagging has been carried out. The parameters characterizing the interaction of a mobile operator with end users are described. The parameters that have the greatest influence on the client’s decision to refuse the services of a mobile operator have been determined.