Customer Churn Prediction in Telecommunication Industry. A Data Analysis Techniques Approach

Denisa Maria Melian (), Andreea Dumitrache (), Stelian Stancu () and Alexandra Nastu ()
Additional contact information
Denisa Maria Melian: Bucharest University of Economic Studies, Bucharest, Romania
Andreea Dumitrache: Bucharest University of Economic Studies, Bucharest, Romania
Stelian Stancu: Bucharest University of Economic Studies, Bucharest, Romania
Alexandra Nastu: Bucharest University of Economic Studies, Bucharest, Romania

Postmodern Openings, 2022, vol. 13, issue 1Sup1, 78-104

Abstract: Telecommunications is one of the most dynamic sectors in the market, where the customer base is an important pawn in receive safe revenues, so is important to focus attention is paid to maintaining them with an active status. Migrating customers from one network to another varies among telecommunication companies depending on different factors such as call quality, pricing plan, minute consumption, data, sms facilities, customer billing issues, etc. Determining an effective predictive model helps detect early warning signals when churn occurs and assigns to each customer a score called “churn score†that indicates the likelihood that the individual might migrate to another network over a predefined time period. To this extent, the present paper uses more than 10k customers sample of a telecommunication company and tries to analyse the churn behavior. The aim of the paper is both to test the efficiency and performance of the most commonly used data mining techniques to predict the churn behavior and to underline the main indicators that can be used when conducting such analyses. Knowing the magnitude of the churn phenomenon, the company can prevent the instability that is going to occur by applying a series of measure in order to increase the retention of the current customers.

Keywords: data mining techniques; churn; customer’s behavior; telecommunication (search for similar items in EconPapers)
JEL-codes: H0 I2 O0 (search for similar items in EconPapers)
Date: 2022
References: Add references at CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
https://lumenpublishing.com/journals/index.php/po/article/view/4931/3595 (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:lum:rev3rl:v:13:y:2022:i:1sup1:p:78-104

DOI: 10.18662/po/13.1Sup1/415

Access Statistics for this article

More articles in Postmodern Openings from Editura Lumen, Department of Economics
Bibliographic data for series maintained by Antonio Sandu ().