Predicting Customers' Churn Using Data Mining Technique and its Effect on the Development of Marketing Applications in Value-Added Services in Telecom Industry

Predicting Customers' Churn Using Data Mining Technique and its Effect on the Development of Marketing Applications in Value-Added Services in Telecom Industry

Sajjad Shokouhyar (Department of Information Management, Management and Accounting Faculty, Shahid Beheshti University, G.C., Tehran, Iran), Parna Saeidpour (Department of Information Management, Management and Accounting Faculty, Shahid Beheshti University, G.C., Tehran, Iran) and Ali Otarkhani (Department of Information Management, Management and Accounting Faculty, Shahid Beheshti University, G.C., Tehran, Iran)
Copyright: © 2018 |Pages: 14
DOI: 10.4018/IJISSS.2018100104

Abstract

This article aims to predict reasons behind customers' churn in the mobile communication market. In this study, different data mining techniques such as logistic regression, decision trees, artificial neural networks, and K-nearest neighbor were examined. In addition, the general trend of the use of the techniques is presented, in order to identify and analyze customers' behavior and discover hidden patterns in the database of an active Coin the field of VAS1for mobile phones. Based on the results of this article, organizations and companies active in this area can identify customers' behavior and develop the required marketing strategies for each group of customers.
Article Preview
Top

Introduction

In recent decades, the human ability to generate and collect data quickly has increased. So analyzing, interpreting and making maximum use of data is difficult and resource demanding due to the exponential growth of many business, governmental and scientific databases. According to (Olutayo & Eludire, 2014) the data mining technique enables organizations to properly utilize their capital of data and promote decision-making.

With the rapid growth of mobile communications' market in recent years, the market has been saturated. Voice and old communications' service has been widespread; hence it is difficult to attract customers by operators. In order to overcome the market today, operators should move toward providing value-added service with higher average revenues, and markets such as communications, entertainment, transfers, information services, rather than the old service. Therefore, in young mobile market in Iran, packages containing valuable service for users can have a potential to earn and attract new customers. In this market, you should always have competitive strategies to exploit future opportunities and face threats of competitors. Customer-focused marketing strategies are important for service providers who want to keep their customers (Chae et al., 2002). Value-added service providers of operators are trying to improve the quality of services, in addition to retaining existing customers, and also attract new customers, including price competition and non-price strategies (Davis, Bagozzi, & Warshaw, 1989; Shokouhyar et al 2018).

According to conducted estimates (Zhao, Wang, & Cha, 2009), reducing customers' churn rate leads to a 6% increase in company profits, and this is significantly important in companies' profitability and growth. In order to prevent customers'churn, customers' behavior is identified with regard to total information and data collected and analysis of potential customers' leaving (churn) and finally targeting those consumers, appropriate and effective strategies are planned and implemented to protect them. In this regard, making an accurate and efficient model is crucial to manage customers' churn (Cossement &Vanden, 2008).

Data mining techniques have caused a major revolution in realizing the concepts of managing customer relationships in great businesses. Data mining capability in operating management concepts, considers customer relationship as a major component of management and its strategies, such as customers' churn management (Nagi, Xiu, & Chau, 2009). Data mining involves searching through databases for potentially useful information, such as knowledge rules, patterns, regularities, and other trends hidden in the data. Today, data mining is more widely used than ever before, not only by businesses who seek profits but also by nonprofit organizations, government agencies, private groups and other institutions in the public sector (Wang, Yan, Chen, & Xing, 2012).

Hence rating and classifying techniques of customers allow managers deal with each customer according to his interests and use each category characteristics to develop appropriate (Baragoin et al., 2001; Shokouhyar et al. 2018).Regarding the principle that for every successful business, understanding customers and their needs is essential, and since customers have different needs we can say utilizing strategies such as direct marketing will not be efficient to provide and introduce new service and products to customers (Zare Ravasan et al., 2015).

Complete Article List

Search this Journal:
Reset
Open Access Articles: Forthcoming
Volume 12: 4 Issues (2020): 1 Released, 3 Forthcoming
Volume 11: 4 Issues (2019)
Volume 10: 4 Issues (2018)
Volume 9: 4 Issues (2017)
Volume 8: 4 Issues (2016)
Volume 7: 4 Issues (2015)
Volume 6: 4 Issues (2014)
Volume 5: 4 Issues (2013)
Volume 4: 4 Issues (2012)
Volume 3: 4 Issues (2011)
Volume 2: 4 Issues (2010)
Volume 1: 4 Issues (2009)
View Complete Journal Contents Listing