Abstract
Customer churn is a critical problem faced by many industries these days. It is 5–10 times more valuable to keep a long-term customer than acquiring a new one. This paper addresses the problem of customer churn with respect to telecommunication industry as churn rate is quite high in this industry (ranging from 10 to 60%) in comparison to others. Predicting customer churn in advance can help these companies in retaining their customers. The paper proposes XGBoost algorithm as a model with the best performance among other state-of-the-art algorithms. The previously used models focus more on the accurate prediction of churners as compared to non-churners, whereas the proposed model classifies churners among the total churners correctly and is able to achieve the highest True positive rate of 81% and AUC score of 0.85. Also, concepts of data transformation, feature selection, and data balancing using oversampling are applied for the same.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Hand D (2007) Principles of data mining. Drug Saf 30:621–622
Osisanwo FY, Akinsola JE, Awodele O et al (2017) Supervised machine learning algorithms: classification and comparison. Inter J Comput Trends Technol 48:128–138
Dalvi PK, Khandge SK, Deomore A et al (2016) Analysis of customer churn prediction in telecom industry using decision trees and logistic regression. In: Symposium on colossal data analysis and networking (CDAN)
Kisioglu P, Topcu YI (2011) Applying bayesian belief network approach to customer churn analysis: a case study on the telecom industry of Turkey. Expert Syst Appl 38:7151–7157
Brandusoiu I, Toderean G (2013) Churn prediction in the telecommunications sector using support vector machines. Margin 1:x1
Lu N, Lin H, Lu J, Zhang G (2014) A customer churn prediction model in telecom industry using boosting. IEEE Trans Ind Inform 10:1659–1665
Adwan O, Faris H, Jaradat K et al (2014) Predicting customer churn in telecom industry using multilayer preceptron neural networks: modeling and analysis. Life Sci J 11(2):75–81
Huang B, Kechadi MT, Buckley B (2012) Customer churn prediction in telecommunications. Expert Syst Appl 39:1414–1425
**a G-E, ** W-D (2008) Model of customer churn prediction on support vector machine. Syst Eng Theor Pract 28:71–77
Amin A, Al-Obeidat F, Shah B et al (2019) Customer churn prediction in telecommunication industry using data certainty. J Bus Res 94:290–301
Azeem M, Usman M, Fong ACM (2017) A churn prediction model for prepaid customers in telecom using fuzzy classifiers. Telecommun Syst 66:603–614
Chen T, Guestrin C (2016) Xgboost: a scalable tree boosting system. In: Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining, pp 785–794
Maclin R, Opitz D (1997) An empirical evaluation of bagging and boosting. AAAI/IAAI, pp 546–551
Ying C, Qi-Guang M, Jia-Chen L, Lin G (2014) Advance and prospects of adaboost algorithm. Acta Automatica Sinica 39:745–758
Friedman JH (2001) Greedy function approximation: a gradient boosting machine. Ann Stat 1:189–232
Pohjalainen V (2017) Predicting service contract churn with decision tree models
Ajit P (2016) Prediction of employee turnover in organizations using machine learning algorithms. Algorithms 4(5):C5
Zhao J, Wang W, Sheng C (2018) Data preprocessing techniques. In: Data driven prediction for industrial process and their applications. Springer, Berlin
Churn in telecom’s dataset. https://www.kaggle.com/becksddf/churn-in-telecoms-dataset. Accessed 20 Sep 2018
Dash M, Liu H (1997) Feature selection for classification. Intell Data Anal 1(3):131–156
Chawla NV, Bowyer KW, Hall LO et al (2002) SMOTE: synthetic minority over-sampling technique. J Artif Intell Res 16:321–357
Jiménez-Valverde A (2012) Insights into the area under the receiver operating characteristic curve (AUC) as a discrimination measure in species distribution modeling. Glob Ecol Biogeogr 2(4):498–507
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Sharma, T., Gupta, P., Nigam, V., Goel, M. (2020). Customer Churn Prediction in Telecommunications Using Gradient Boosted Trees. In: Khanna, A., Gupta, D., Bhattacharyya, S., Snasel, V., Platos, J., Hassanien, A. (eds) International Conference on Innovative Computing and Communications. Advances in Intelligent Systems and Computing, vol 1059. Springer, Singapore. https://doi.org/10.1007/978-981-15-0324-5_20
Download citation
DOI: https://doi.org/10.1007/978-981-15-0324-5_20
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-15-0323-8
Online ISBN: 978-981-15-0324-5
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)