Literature Review of Using DWHBI Approaches to Predict and Reduce Customer Churn in Telecommunications Industry

Authors

  • K. Prakash Krishnan  Ph.D Scholar, Department of Computer science, Chikkanna Govt Arts College, Tirupur, Tamil Nadu, India
  • Dr. A. Kumar Kombaiya  Assistant Professor, Department of Computer Science, Chikkanna Govt Arts College, Tirupur, Tamil Nadu, India

DOI:

https://doi.org/10.32628/CSEIT206535

Keywords:

Churn prediction, Churn prevention, data mining, Data warehouse and Business Intelligence, Key performance indicators [KPI model], Big data, Hive Ingestion platform, Kafka, Customer retention, campaign offers, churn model score, customer life cycle process, Performance metrics, Predictive models, ARPU

Abstract

In recent days, telecom industry plays a vital role in our daily life. During corona period entire world depends on the telecom services domain. But telecome industry has been facing many surivival problems in the global market since last 10 years due to heavy competition between competitors. To stand in this field, service providers have to understand the complete customer requirements and provide the efficient services to stop the customer movement from one network to another network. Customer churn is one of the most critical problem faced by the telecom industry. In this industry, it is more expensive to bring the new customers as compared to retain the existing customers. The objective of customer churn prediction is to find the subscribers that are ready to move from the current service provider in advance. Churn prediction allows the service providers to offer new benefits and campaign offers to retain the existing customer in the same network. Technically this term would be call it as ‘Win back Situation’ in telecom industry. The high volume of data generated by telecom industry , with the help of data warehosuing and business intelligence implementation would become the main asset for predicting the customer churn. To prevent the churn many models and methods are used by researchers. In this paper, we reviewed different mining methods and the most popular algorithms which used in telecom industry. But this model is not only for telecom domain, it can be implement for other domains which has highly depends on customer interactions.

References

  1. Yu, R., An, X., Jin, B. et al. Particle classification optimization-based BP network for telecommunication customer churn prediction. Neural Comput & Applic 29, 707–720 (2018)
  2. Ahmad, A.K., Jafar, A. & Aljoumaa, K. Customer churn prediction in telecom using machine learning in big data platform. J Big Data 6, 28 (2019)
  3. Pamina J., Beschi Raja J., Sam Peter S., Soundarya S., Sathya Bama S., Sruthi M.S. (2020) Inferring Machine Learning Based Parameter Estimation for Telecom Churn Prediction. In: Smys S., Tavares J., Balas V., Iliyasu A. (eds) Computational Vision and Bio-Inspired Computing. ICCVBIC 2019. Advances in Intelligent Systems and Computing, vol 1108. Springer, Cham
  4. Adnan Amin, Sajid Anwar (2016) Custome churn prediction in Telecom using Rough set approach Neuro computing 237(2017)242-254. 2016 Elsevier B.V. All rights reserved.
  5. Kim , J.Lee improved churn prediction in telecom industry by analyzing a large network , Expert syst. Appl 41 (15) (2014) 6575-6584
  6. Maurus Riedweg , Pavol Svaba and Gwendolin Wilke (2018) Revenue Optimization of Tele marketing campaigns for prepaid customers. 18714.1PFES-ES.
  7. Umayaparvathi , K.Iyakutti (2016) A survey on customer churn prediction in Telecom industry : Datasets, mehtods and metrics ISSN: 2395 -0056

Downloads

Published

2020-10-30

Issue

Section

Research Articles

How to Cite

[1]
K. Prakash Krishnan, Dr. A. Kumar Kombaiya, " Literature Review of Using DWHBI Approaches to Predict and Reduce Customer Churn in Telecommunications Industry" International Journal of Scientific Research in Computer Science, Engineering and Information Technology(IJSRCSEIT), ISSN : 2456-3307, Volume 6, Issue 5, pp.176-180, September-October-2020. Available at doi : https://doi.org/10.32628/CSEIT206535