Abstract
Aiming at overcoming the shortcomings of common telecommunication customer churn prediction models as single model and poor classification performance, a gradient decision tree integration model (GBDT) prediction model is proposed, and the important parameters are searched by harmonic search algorithm (HS). We built a telecom customer churn prediction model based on HS-GBDT algorithm. This model compares the parameter combinations to be optimized in the GBDT algorithm into the synthesized harmony in the HS algorithm, and seeks the optimal parameter combination of the GBDT model through continuous iteration of the harmony. The experimental results show that the combined model has higher classification accuracy than Logistic regression, support vector machine and random forest, and can provide good decision support for major telecom operators in the process of customer churn management.
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
References
Qin, H.F.: The application of data mining in telecommunication churn customer. Res. J. Appl. Sci. Eng. Technol. 4(11), 1504–1507 (2012)
Yu, X.B., Cao, J., Gong, Z.W.: Review on customer churn issue. Comput. Integr. Manuf. Syst. 18(10), 2253–2263 (2016)
Friedman, J.H.: Greedy function approximation: a gradient boosting machine. Ann. Stat. 29(5), 1189–1232 (2001)
Zhang, W., Yang, S.L., Liu, T.T.: Customer churn prediction in mobile communication enterprises based on CART and boosting algorithm. Chin. J. Manag. Sci. 22(10), 90–96 (2014)
Ding, J.M., Liu, G.Q., Li, H.: The application of improved random forest in the telecom customer churn prediction. Pattern Recogn. Artif. Intell. 28(11), 1041–1049 (2015)
Li, R.Q.: Churn Prediction Models for Anonymous Telecom Customer Dataset. University of Science and Technology of China, Beijing (2017)
Geem, J., Kim, J.H., Loganathan, G.V.: A new heuristic optimization algorithm: harmony search. Simulation 76(2), 60–68 (2001)
Ding, J.L., Li, L.S.: Network traffic predicting based on SVM optimized by harmony search algorithm. Microcomput. Appl. 33(01), 67–70 (2017)
Guo, W.Y.: Research on Selective Ensemble Algorithm Based on Support Vector Machine. Heifei University of Technology, Heifei (2015)
Schapire, R.E., Freund, Y., Bartlett, P.: Boosting the margin: a new explanation for the effectiveness of voting methods. Ann. Stat. 26(5), 1651–1686 (1998)
Li, H.: Statistical Learning Method. Tsinghua University Press, Beijing (2012)
Zhang, X.: Quantitative Investment Model Based on Improved GBDT. Guangxi University, Nanning (2018)
Acknowledgment
This paper was supported in part by the Postgraduate Research & Practice Innovation Program of Jiangsu Province under Grant No. KYCX19-0874, National Natural Science Foundation of China under Grant No 11801267, and the Natural Science Foundation of the Jiangsu Higher Education Institutions of China under Grant No. 18KJB520007.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Liang, X., Chen, S., Chen, C., Zhang, T. (2019). Research on Telecom Customer Churn Prediction Method Based on Data Mining. In: Sun, Y., Lu, T., Yu, Z., Fan, H., Gao, L. (eds) Computer Supported Cooperative Work and Social Computing. ChineseCSCW 2019. Communications in Computer and Information Science, vol 1042. Springer, Singapore. https://doi.org/10.1007/978-981-15-1377-0_38
Download citation
DOI: https://doi.org/10.1007/978-981-15-1377-0_38
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-15-1376-3
Online ISBN: 978-981-15-1377-0
eBook Packages: Computer ScienceComputer Science (R0)
