Machine Learning as Intelligent tool for Churn Prediction in Telecommunication Industry

Print
 
Download Full Text
International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
Volume 181 - Number 10
Year of Publication: 2018
Authors:
Megha Gupta, Anju Bhandari Gandhi, S. C. Gupta
10.5120/ijca2018917621

Megha Gupta, Anju Bhandari Gandhi and S C Gupta. Machine learning as intelligent tool for churn prediction in Telecommunication Industry. International Journal of Computer Applications 181(10):16-22, August 2018. BibTeX

@article{10.5120/ijca2018917621,
	author = {Megha Gupta and Anju Bhandari Gandhi and S. C. Gupta},
	title = {Machine learning as intelligent tool for churn prediction in Telecommunication Industry},
	journal = {International Journal of Computer Applications},
	issue_date = {August 2018},
	volume = {181},
	number = {10},
	month = {Aug},
	year = {2018},
	issn = {0975-8887},
	pages = {16-22},
	numpages = {7},
	url = {http://www.ijcaonline.org/archives/volume181/number10/29808-2018917621},
	doi = {10.5120/ijca2018917621},
	publisher = {Foundation of Computer Science (FCS), NY, USA},
	address = {New York, USA}
}

Abstract

In most of the sectors dominated by the cost of changing the landscape, wear of the activities is painted or blurred by the clients (clients who wish to modify or change their suppliers for various reasons). This phenomenon is widespread in the telecommunications industry and all aspects related to its lead to the belief that it increases sharply. Since the market is very competitive and the number of prepaid customers, "it increases, it is vital that companies to actively confront with the distraction of customers, the identification of behaviour that could ultimately be created." In this article we have proposed A hybrid model machine learning to predict distortion in mobile telecommunications networks The experiments were carried out using a variety of tools for machine learning, together with a set of real data from the open data provider to evaluate the manufacturer's productivity. The results show that the new hybrid model is more accurate than the individual methods. Auto learning is a subset of artificial intelligence, commonly used statistical techniques to give computers the ability to "learn" the data.

References

  1. Praveen et al., Churn Prediction in Telecom Industry Using R, International Journal of Engineering and Technical Research (IJETR) ISSN: 2321-0869, Volume-3, Issue-5, May 2015.
  2. Chuanqi Wang, Ruiqi Li, Peng Wang, ZonghaiChen,“Partition costsensitive CART based on customer value for Telecom customer Churn Prediction, Control Conference (CCC), September 2017
  3. U.S. Commercial Service Vietnam, “Vietnam Market for Telecommunications Equipment and Services,” The U.S. Commercial Service, 2014.
  4. Saravanan, M., Manoj, P., Smitha, G. B., & Lakshmi, V. (2015). Aatish-A New Profile-Based Recommendation Services for Mobile Telecom Network Subscribers. In Network Intelligence Conference (ENIC), 2015 Second European (pp. 160-164).
  5. R. Punnoose and P. Ajit, “Prediction of employee turnover in organizations using machine learning algorithms,” Int. J. Adv. Res. Artif. Intell., vol. 5, no. 9, 2016.
  6. Ionuţ Brânduşoiu, Gavril Toderean, and Horia Beleiu "Methods for churn prediction in the pre-paid mobile telecommunications industry." In 2016 International Conference on Communications (COMM), pp. 97-100. IEEE, 2016.
  7. A. Perianez, A. Saas, A. Guitart, and C. Magne. Churn prediction in mobile social games: Towards a complete assessment using survival ensembles. In 2016 IEEE International Conference on Data Science and Advanced Analytics (DSAA), pages 564–573, Oct 2016.
  8. M. Arjovsky, S. Chintala, and L. Bottou, “Wasserstein gan,” arXiv preprint arXiv: 1701.07875, 2017.
  9. R. Johnson and T. Zhang, “Effective use of word order for text categorization with convolutional neural networks,” arXiv preprint arXiv: 1412.1058, 2014.
  10. T. Sumathi. “Churn Prediction on Huge Sparse Telecom Data Using Meta-heuristic.” International Journal of Advanced Research in Computer and Communication Engineering (IJARCCE), vol.5, no.7, pp.574-577, 2016
  11. Reinartz, Werner J., and Vita Kumar. "The impact of customer relationship characteristics on profitable lifetime duration." Journal of marketing 67, no. 1 (2003): 77-99.
  12. Sohn, So Young, and Yoonseong Kim. "Searching customer patterns of mobile service using clustering and quantitative association rule." Expert systems with Applications 34, no. 2 (2008): 1070-1077.
  13. Thomassey, Sébastien, and Antonio Fiordaliso. "A hybrid sales forecasting system based on clustering and decision trees." Decision Support Systems 42, no. 1 (2014): 408-421.
  14. Wei, Chih-Ping, and I-Tang Chiu. "Turning telecommunications call details to churn prediction: a data mining approach." Expert systems with applications 23, no. 2 (2002): 103-112.

Keywords

Churn prediction, logistic regression, and telecommunications, voted perceptron.