Implementation of a Customer Churn Model Using XGBoost and SHAP for Telecommunication Customers
Keywords:
Customer Churn, SHAP, SMOTE, Telecommunications, XGBoostAbstract
Customer churn is a condition in which customers stop using telecommunications services, potentially reducing revenue and customer loyalty while increasing customer acquisition costs. This study implements XGBoost with Synthetic Minority Over-sampling Technique (SMOTE) to address class imbalance and Shapley Additive exPlanations (SHAP) to interpret the factors contributing to churn predictions. The dataset used is the Telecom Customer Churn dataset from Maven Analytics, consisting of 7,043 customer records, with 6,589 records used after excluding customers with Joined status. The optimized XGBoost model achieved a Recall of 77.72%, an F1-score of 77.93%, and a ROC-AUC of 93.73%. SHAP analysis identified the factors contributing to customer churn predictions, while validation using Churn Category and Churn Reason showed that Competitor, Price, and Dissatisfaction accounted for 73.46% of churned customers. The most frequent churn reasons were Competitor had better devices (313 customers), Competitor made better offer (311 customers), and Attitude of support person (220 customers). The results provide analytical support for identifying customers likely to churn and understanding factors associated with churn predictions.
References
R. Sinaga and S. Widianto, “Understanding Telecommunication Customer Churn: Insights from LightGBM Predictive Modelling and SHAP Feature Interpretation,” ASEAN Mark. J., vol. 15, no. 1, 2023, doi: 10.7454/amj.v15i1.1229.
J. Bergstra and Y. Bengio, “Random search for hyper-parameter optimization,” J. Mach. Learn. Res., vol. 13, pp. 281–305, 2012.
B. Bischl et al., “Hyperparameter optimization: Foundations, algorithms, best practices, and open challenges,” Wiley Interdiscip. Rev. Data Min. Knowl. Discov., vol. 13, no. 2, pp. 1–43, 2023, doi: 10.1002/widm.1484.
E. L. Luma, F. Tat, and Y. Dion, “Hubungan Antara Tingkat Pengetahuan Ibu Tentang Penyakit Pneumonia Dengan Perilaku Pencegahan Pneumonia Pada Anak Di Puskesmas Bakunase Kota Kupang,” CHMK Appl. Sci. J., vol. 4, no. 1, pp. 18–28, 2021.
Y. D. Esdin Lestari Lumaa, Florentianus Tat, “CHM-K Applied Scientific Journals,” Hub. Antara Tingkat Pengetah. Ibu Tentang Penyakit Pneumonia Dengan Perilaku Pencegah. Pneumonia Pada Anak Di Puskesmas Bakunase Kota Kupang, vol. 4, pp. 18–28, 2021, doi: 10.37792/casj.v4i1.962.
N. Y. Nhu, T. Van Ly, and D. V. Truong Son, “Churn prediction in telecommunication industry using kernel Support Vector Machines,” PLoS One, vol. 17, no. 5 May, 2022, doi: 10.1371/journal.pone.0267935.
C. Kaope and Y. Pristyanto, “The Effect of Class Imbalance Handling on Datasets Toward Classification Algorithm Performance,” MATRIK J. Manajemen, Tek. Inform. dan Rekayasa Komput., vol. 22, no. 2, pp. 227–238, 2023, doi: 10.30812/matrik.v22i2.2515.
H. A. Rasool, K. K. Aljawaheri, and A. A. M. Karram, “Explainable Customer Churn Prediction in Telecom Using Ensemble Learning and SHAP Analysis,” Math. Model. Eng. Probl., vol. 12, no. 12, pp. 4373–4386, 2025, doi: 10.18280/mmep.121226.
L. N. Wakhidah, A. K. Zyen, and B. B. Wahono, “Evaluation of Telecommunication Customer Churn Classification with SMOTE Using Random Forest and XGBoost Algorithms,” J. Appl. Informatics Comput., vol. 9, no. 1, pp. 89–95, 2025, doi: 10.30871/jaic.v9i1.8740.
K. Peng and Y. Peng, “Research on Telecom Customer Churn Prediction Based on GA-XGBoost and SHAP,” J. Comput. Commun., vol. 10, no. 11, pp. 107–120, 2022, doi: 10.4236/jcc.2022.1011008.
I. G. A. R. Astarani and L. A. A. R. Putri, “Klasifikasi Customer Churn Menggunakan XGBoost dengan Optimasi GridSearchCV Berbasis Shapley Additve Explanations,” J. Nas. Teknol. Inf. dan Apl., vol. 4, no. November, pp. 1–10, 2025.
N. Dwi Ramadhanti and R. Nurfitriana Handayani, “Analisis Sentimen Ulasan Pengguna Aplikasi Shopee di Google Play Store Menggunakan Support Vector Machine dengan Teknik SMOTE,” J. Inform. Polinema, vol. 12, no. 2, pp. 313–322, 2026, doi: 10.33795/jip.v12i2.9073.
M. Z. Alotaibi and M. A. Haq, “Customer Churn Prediction for Telecommunication Companies using Machine Learning and Ensemble Methods,” Eng. Technol. Appl. Sci. Res., vol. 14, no. 3, pp. 14572–14578, 2024, doi: 10.48084/etasr.7480.
J. A Ilemobayo et al., “Hyperparameter Tuning in Machine Learning: A Comprehensive Review,” J. Eng. Res. Reports, vol. 26, no. 6, pp. 388–395, 2024, doi: 10.9734/jerr/2024/v26i61188.
D. Wahyu, K. H. Sakaro, N. Sabrina, E. Ramadhan, and K. Kunci, “Klasifikasi Churn Dengan Algoritma XGBoost Menggunakan Feature Selection Boruta-Shap,” Technol. Sci., vol. 7, no. 2, pp. 1193–1201, 2025, doi: 10.47065/bits.v7i2.7965.
A. Sikri, R. Jameel, S. M. Idrees, and H. Kaur, “Enhancing customer retention in telecom industry with machine learning driven churn prediction,” Sci. Rep., vol. 14, no. 1, pp. 1–13, 2024, doi: 10.1038/s41598-024-63750-0.
A. El Attar and M. El-Hajj, “Explainable AI-driven customer churn prediction: a multi-model ensemble approach with SHAP-based feature analysis,” Front. Artif. Intell., vol. 9, no. 1, 2026, doi: 10.3389/frai.2026.1748799.
H. A. Mengash, N. Alruwais, F. Kouki, C. Singla, E. S. Abd Elhameed, and A. Mahmud, “Archimedes Optimization Algorithm-Based Feature Selection with Hybrid Deep-Learning-Based Churn Prediction in Telecom Industries,” Biomimetics, vol. 9, no. 1, 2024, doi: 10.3390/biomimetics9010001.
S. Antoh, R. Herteno, I. Budiman, D. Kartini, and M. I. Mazdadi, “Prediksi Churn Pelanggan Telekomunikasi dengan Optimalisasi Seleksi Fitur dan Tuning Hyperparameter pada Algoritma Klasifikasi C4.5,” J. Sist. Inf. Bisnis, vol. 15, no. 1, pp. 60–67, 2025, doi: 10.14710/vol15iss1pp60-67.
B. Prabadevi, R. Shalini, and B. R. Kavitha, “Customer churning analysis using machine learning algorithms,” Int. J. Intell. Networks, vol. 4, no. April, pp. 145–154, 2023, doi: 10.1016/j.ijin.2023.05.005.
R. Suguna, J. Suriya Prakash, H. Aditya Pai, T. R. Mahesh, V. Vinoth Kumar, and T. E. Yimer, “Mitigating class imbalance in churn prediction with ensemble methods and SMOTE,” Sci. Rep., vol. 15, no. 1, pp. 1–20, 2025, doi: 10.1038/s41598-025-01031-0.
X. Zhang, A. Ghosh, and D. A. Ali, “Research on Marketing Strategy Management based on Customer Retention,” Acad. J. Manag. Soc. Sci., vol. 6, no. 2, pp. 66–70, 2024, doi: 10.54097/rdcx2907.
O. Rainio, J. Teuho, and R. Klén, “Evaluation metrics and statistical tests for machine learning,” Sci. Rep., vol. 14, no. 1, pp. 1–14, 2024, doi: 10.1038/s41598-024-56706-x.
Z. M. Altukhi, S. Pradhan, and N. Aljohani, “A Systematic Literature Review of the Latest Advancements in XAI,” Technologies, vol. 13, no. 3, 2025, doi: 10.3390/technologies13030093.
S. M. Lundberg and S. I. Lee, “A unified approach to interpreting model predictions,” Adv. Neural Inf. Process. Syst., vol. 2017-Decem, no. Section 2, pp. 4766–4775, 2017.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Ahmad Maulana, Rissa Nurfitriana Handayani
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish articles in Jurnal PTIPD: Penelitian Terapan Informatika dan Pengembangan Data agree to the following terms:
- Authors retain copyright of the article and grant the journal right of first publication with the work simultaneously licensed under a CC-BY-SA or The Creative Commons Attribution–ShareAlike License.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
