Churn Prediction in Internet Service Provider Companies

Churn Prediction in Internet Service Provider Companies

İlayda Ülkü (Istanbul Kültür University, Turkey), Mehmet Yahya Durak (Istanbul Kültür University, Turkey) and Fadime Üney-Yüksektepe (Istanbul Kültür University, Turkey)
Copyright: © 2016 |Pages: 17
DOI: 10.4018/978-1-5225-0075-9.ch013
OnDemand PDF Download:
$37.50

Abstract

As a basic standard of life, internet connects millions of computers in a global network. People use, participate, or access the internet with the help of internet service providers (ISPs). To have better quality of connection, customers are prone to change their ISPs. In the competitive environment, ISPs endeavor to prevent losing their customers which are referred as churn. Thus, churn management takes an important place for ISPs. To investigate customer loyalty status, behavior, and information of the churn possibility in Turkey, a questionnaire is implemented. By using a real data obtained from a survey, promising and applicable results are obtained to predict the churn behavior of ISP customers in Turkey. As an extension of the study, the questionnaire will be applied for a larger population to find accurate results about churn situations. This study will help ISP companies to determine the required advertising campaigns for the customers.
Chapter Preview
Top

Background

Data mining applications can be used in various areas such as, medicine, banking/finance, transportation, sale/marketing, health care and insurance, etc. (Brachman et. al., 1996). To identify the prediction of customer churn situation, a paper is studied by M. Owczarczuk (Owczarczuk, 2010) with the help of logistic regression. Likewise, Nie et al. studied with logistic regression (Nie, 2011). However, they expand their study and decision tree model is added to find accurate predictions. There is another study proposed by Shim et al where logistic regression and decision tree is used (Shim et al., 2012). They also extend their study by applying neural network to classify the customers. In addition, Binomial logistic regression model is studied by Keramati and Ardabili to predict customer churn (Keramati & Ardabili, 2011).

Complete Chapter List

Search this Book:
Reset