Integrating Traditional ML Models: A Hybrid Ensemble Churn Prediction Framework
Keywords:
Customer churn prediction, Hybrid ensemble model, Traditional machine learning, Gradient Boosting Machine (GBM), Random Forest (RF), XGBoost, Stacking ensemble, Customer retention, Predictive analytics.Abstract
Customer Churn Prediction is useful to identify and retain important customers to avoid any business losses. The traditional Machine Learning algorithm provides outstanding results to evaluate the customer information, but these algorithms are unable to detect complex patterns about customers’ behavior. This paper designates a Hybrid Ensemble Churn Prediction Model, which uses multiple prevalent Machine Learning algorithms such as GBM and RF along with a higher level of meta-learning that uses XGBoost. The purpose is to make use of stacking to improve model robustness to predictions and avoid misclassifications to boost customers’ recall. Theoretical validation shows that this hybrid ensemble can outperform GBM and RF on Accuracy, F1-score, and AUC values to make this algorithm a best choice to formulate customers’ retention strategy.Downloads
References
X. Xiahou and Y. Harada, “B2C e-commerce customer churn prediction based on K-Means and SVM,” J. Theor. Appl. Electron. Commer. Res., vol. 17, no. 2, pp. 458–475, 2022.DOI: 10.3390/jtaer17020024
M. I. et al., “Customer Churn Prediction: A Systematic Review of Recent Advances, Trends, and Challenges in Machine Learning and Deep Learning,” Mach. Learn. Knowl. Extr., vol. 7, no. 3, 2025.
DOI: 10.3390/make7030105
A. Bhatnagar and S. Srivastava, “Customer Churn Prediction: A Machine Learning Approach with Data Balancing for Telecom Industry,” Int. J. Computing, vol. 24, no. 1, 2024.DOI: 10.47839/ijc.24.1.3873
Md A. Al Rahib, N. Saha, R. Mia, and A. Sattar, “Customer data prediction and analysis in e-commerce using machine learning,” Bull. Electr. Eng. Inform., vol. 13, no. 4, 2024.DOI: 10.11591/eei.v13i4.6420
J. Friedman, “Greedy function approximation: A gradient boosting machine,” Ann. Stat., vol. 29, no. 5, pp. 1189–1232, 2001.DOI: 10.1214/aos/1013203451
L. Breiman, “Random forests,” Mach. Learn., vol. 45, pp. 5–32, 2001.
DOI: 10.1023/A:1010933404324
Y. LeCun, Y. Bengio, and G. Hinton, “Deep learning,” Nature, vol. 521, pp. 436–444, 2015.
DOI: 10.1038/nature14539
T. Chen and C. Guestrin, “XGBoost: A scalable tree boosting system,” KDD, pp. 785–794, 2016.
DOI: 10.1145/2939672.2939785
W. Verbeke et al., “A comprehensive study on churn prediction in the telecommunications industry,” Expert Syst. Appl., 2011.DOI: 10.1016/j.eswa.2011.01.027
M. Gupta and S. Tripathy, “Customer churn prediction in e-commerce: A machine learning approach,” Int. J. Data Sci. Anal., 2020.DOI: 10.1007/s41060-018-0158-0
A. Amin et al., “Churn analysis using behavioral logs and usage patterns,” J. Ambient Intell. Humanized Comput., 2021.DOI: 10.1007/s12652-020-01855-4
Z. Huang, H. Chen, and C. Zeng, “Applying data mining to telecom churn prediction,” IEEE ICDM, 2018.
DOI: 10.1109/ICDM.2018.00015
S. Zhang, A. Chen, and P. Zhou, “A hybrid ensemble model for customer churn prediction using stacking,” Procedia Comput. Sci., vol. 199, pp. 450–457, 2022.DOI: 10.1016/j.procs.2022.01.057
A. Khattak et al., “A hybrid BiLSTM–CNN model for churn prediction,” Telecommun. Syst., 2023.
DOI: 10.1007/s11235-023-01060-w
N. V. Chawla, K. W. Bowyer, L. O. Hall, and W. Kegelmeyer, “SMOTE: Synthetic Minority Oversampling Technique,” J. Artif. Intell. Res., vol. 16, pp. 321–357, 2002.DOI: 10.1613/jair.953
T. Verbeke, D. Martens, C. Mues, and B. Baesens, “Building comprehensible churn prediction models using rule induction,” Expert Syst. Appl., 2012.DOI: 10.1016/j.eswa.2011.10.027
A. Idris, M. Rizwan, and A. Khan, “Churn prediction using boosting and bagging,” Eng. Appl. Artif. Intell., vol. 36, pp. 249–257, 2014.DOI: 10.1016/j.engappai.2014.07.001
W. Wang et al., “Customer behavior prediction using deep learning,” IEEE Access, 2018.
DOI: 10.1109/ACCESS.2018.2832981
T. Fader and B. Hardie, “Customer-base analysis using Pareto/NBD models,” Marketing Science, 2010.
DOI: 10.1287/mksc.1090.0505
A. Graves, “Long short-term memory,” Neural Comput., vol. 9, no. 8, pp. 1735–1780, 1997.
DOI: 10.1162/neco.1997.9.8.1735
V. Kumar and S. Gupta, “Customer churn prediction using recurrent networks,” Information Systems Frontiers, 2019.DOI: 10.1007/s10796-018-9865-3
H. He and E. Garcia, “Learning from imbalanced data,” IEEE Trans. Knowl. Data Eng., 2009.
DOI: 10.1109/TKDE.2008.239
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
