Friday 17th of November 2017
 

Predicting Customer Churn in Mobile Telephony Industry Using Probabilistic Classifiers in Data Mining


Clement Kirui, Li Hong, Wilson Cheruiyot and Hillary Kirui

Customer churn in the mobile telephony industry is a continuous problem owing to stiff competition, new technologies, low switching costs, deregulation by governments, among other factors. To address this issue, players in this industry must develop precise and reliable predictive models to identify the possible churners beforehand and then enlist them to intervention programs in a bid to retain as many customers as possible. This paper proposes a new set of features with the aim of improving the recognition rates of possible churners. The features are derived from call details and customer profiles and categorized as contract-related, call pattern description, and call pattern changes description features. The features are evaluated using two probabilistic data mining algorithms Nave Bayes and Bayesian Network, and their results compared to those obtained from using C4.5 decision tree, a widely used algorithm in many classification and prediction tasks. Experimental results show improved prediction rates for all the models used.

Keywords: Customer churn, data mining, classification / prediction, decision tree, NaÔve Bayes and Bayesian Network.

Download Full-Text


ABOUT THE AUTHORS

Clement Kirui
Clement Kirui received his Bachelorís degree (Information Technology) from Jomo Kenyatta University of Agriculture and Technology, Kenya, in 2008 and is currently pursuing his Masterís degree (Computer Application Technology) in Central South University, China. He has previously worked with Acrobat Research Limited, Kenya (a market research firm) and currently works with the Municipal Council of Bomet, Kenya, at the IT Department. He is a Cisco Certified Network Associate (CCNA) and a Microsoft Certified Professional (MCP), with three Microsoft IT Professional certifications (MCITP Database Administrator 2008, MCITP Database Developer 2008, and MCITP Business Intelligence Developer 2008). He has co-authored one paper and five more are currently under review in different refereed journals. His research interests include Database Systems, Business Intelligence, Data Mining, Business Information Systems, and Internet Technologies.

Li Hong
Hong Li received his Bachelorís and Masterís degrees from Peking University and PhD degree from Central South University in 2007. He is a professor and the director of the Department of Information and Communication Engineering, Central South University. His main research interests are data mining and DSP. He has published many papers in different refereed journals and conferences and has supervised students since 2001.

Wilson Cheruiyot
Wilson Cheruiyot received his Bachelorís degree (Mathematics and computer science) from Jomo Kenyatta University of Agriculture and Technology, Kenya, in 1994. He received his Masterís degree and PhD (Computer Application Technology) both from Central South University, China, in 2002 and 2012 respectively. He is also a Microsoft Certified Professional (MCP) and a Microsoft Certified Database Administrator (MCDBA). He has previously worked with the Teachers Service Commission of Kenya and with the Kenya National Audit Office (KENAO). He is currently a professor of Computer Science at the Computing Department, Jomo Kenyatta University of Agriculture and Technology, Kenya. He has published over eleven papers in different refereed journals. His best paper award was a paper submitted to Springerlink journal of Multimedia systems, titled ďQuery quality refinement in singular value decomposition to improve genetic algorithms for multimedia data retrievalĒ, whose impact factor was 1.176 and indexed by SCI and EI Compendex. Currently, he reviews articles for the Journal of Petroleum and Gas Engineering, www.academicjournals.org/JGE, and the Journal of Engineering and Technology Research, www.academicjournals.org/JETR/index.htm. His current research interests are: Multimedia Data Retrieval, Internet of Things, Evolutionary Computation for Optimization, Digital Image Processing, and ICT for Development.

Hillary Kirui
Hillary Kirui received his Bachelorís degree (Electronics and Computer Engineering) from Jomo Kenyatta University of Agriculture and Technology, Kenya, in 2008 and is currently pursuing his Masterís degree (ICT Policy & Regulation) at the same university. He has previously worked with Rapid Communications Limited, Kenya (a telecommunications firm) and currently works with the Kenya Airways Limited in the Flight Operations Department. He is a Cisco Certified Network Associate (CCNA) and is presently undertaking Cisco Certified Network Professional (CCNP) certification. His research interests include Data Communications, Network Security, ICT Policy Analysis, and ICT Regulatory Frameworks.


IJCSI Published Papers Indexed By:

 

 

 

 
About IJCSI

IJCSI is a refereed open access international journal for scientific papers dealing in all areas of computer science research...

Learn more »
Join Us
FAQs

Read the most frequently asked questions about IJCSI.

Frequently Asked Questions (FAQs) »
Get in touch

Phone: +230 911 5482
Email: info@ijcsi.org

More contact details »