Development of XAI-Driven Churn Prediction Framework for Proactive Retention in Telecom

Fatima Zaka; Maham Sabir; Laraib Khalid; Sidra Ejaz; Sobia Khalid

Authors

Fatima Zaka Department of Software Engineering (Fatima Jinnah Women University, Rawalpindi, Pakistan).
Maham Sabir Department of Software Engineering (Fatima Jinnah Women University, Rawalpindi, Pakistan).
Laraib Khalid Department of Software Engineering (Fatima Jinnah Women University, Rawalpindi, Pakistan).
Sidra Ejaz Department of Software Engineering (Fatima Jinnah Women University, Rawalpindi, Pakistan).
Sobia Khalid Department of Software Engineering (Fatima Jinnah Women University, Rawalpindi, Pakistan).

Keywords:

Churn Prediction, Explainable AI, Customer Segmentation, Shap Values and Catboost

Abstract

In the telecommunications industry, customer churn is a major problem that has a big influence on profitability and competitiveness. Current systems mostly rely on reactive strategies that are unable to prevent churn proactively. We present an intelligent, explainable AI-driven system, TeleChurnAI, which predicts churn and pinpoints its root causes. The novelty of this research lies in its integration of explainable AI and customer segmentation, providing useful information for retention strategies. To develop TeleChurnAI, a machine learning model, CatBoost, is employed to accurately predict churn, and SHAP (Shapley Additive exPlanations) is utilized to interpret model results as well as to support predictions. The prediction accuracy and interpretability of the model are assessed after it is trained on the historical telecom customer dataset, “Telco Customer Churn”. We found that TeleChurnAI offers transparency through visual explanations of churn risk factors and significantly increases the accuracy of churn predictions. Through an interactive dashboard made for CRM professionals with different levels of technical expertise, using the Shiny framework in Python, the system also divides up the customer base according to demographic and behavioral trends, allowing for targeted retention actions. In addition to helping with early intervention, this dual capability lowers marketing expenses and boosts customer loyalty. In conclusion, TeleChurnAI provides a thorough and user-centered method for telecom churn management. In the future, we aim to integrate sentiment analysis and real-time prediction in our proposed system.

References

A. O. A. Ibrahim Adedeji Adeniran, Christianah Pelumi Efunniyi, Olajide Soji Osundare, “Implementing machine learning techniques for customer retention and churn prediction in telecommunications,” Comput. Sci. IT Res. J., vol. 5, no. 8, pp. 2011–2025, 2024, doi: https://doi.org/10.51594/csitrj.v5i8.1489.

S. H. G. Sharmila K. Wagh, Aishwarya A. Andhale, Kishor S. Wagh, Jayshree R. Pansare, Sarita P. Ambadekar, “Customer churn prediction in telecom sector using machine learning techniques,” Results Control Optim., vol. 14, p. 100342, 2024, doi: https://doi.org/10.1016/j.rico.2023.100342.

M. T. Sumana Sharma Poudel, Suresh Pokharel, “Explaining customer churn prediction in telecom industry using tabular machine learning models,” Mach. Learn. with Appl., vol. 17, p. 100567, 2024, doi: https://doi.org/10.1016/j.mlwa.2024.100567.

A. Chowdhury, S. Kaisar, M. M. Rashid, S. S. Shafin, and J. Kamruzzaman, “Churn Prediction in Telecom Industry using Machine Learning Ensembles with Class Balancing,” 2021 IEEE Asia-Pacific Conf. Comput. Sci. Data Eng. CSDE 2021, 2021, doi: 10.1109/CSDE53843.2021.9718498.

W. C. Y. Shuli Wu, “Integrated Churn Prediction and Customer Segmentation Framework for Telco Business,” IEEE access, 2021, [Online]. Available: https://ieeexplore.ieee.org/document/9406002

S. S. K. S. Arockia Panimalar, A. Krishnakumar, “Intensified Customer Churn Prediction: Connectivity with Weighted Multi-Layer Perceptron and Enhanced Multipath Back Propagation,” Expert Syst. Appl., vol. 265, p. 125993, 2025, doi: https://doi.org/10.1016/j.eswa.2024.125993.

A. Senthilselvi, V. Kanishk, K. Vineesh, and A. Praveen Raj, “A Novel Approach to Customer Churn Prediction in Telecom,” Proc. - 3rd Int. Conf. Adv. Comput. Commun. Appl. Informatics, ACCAI 2024, 2024, doi: 10.1109/ACCAI61061.2024.10602345.

S. Dhariya, “Customer Churn Prediction in Telecommunication Industry using Machine Learning and Deep Learning Approach,” 3rd Int. Conf. Innov. Mech. Ind. Appl. ICIMIA 2023 - Proc., pp. 804–810, 2023, doi: 10.1109/ICIMIA60377.2023.10426097.

D. A. Kumar, A. Choudhary, and A. Chaudhary, “Churn Prediction Model of Telecom Industry,” Proc. - IEEE 2023 5th Int. Conf. Adv. Comput. Commun. Control Networking, ICAC3N 2023, pp. 1–6, 2023, doi: 10.1109/ICAC3N60023.2023.10541596.

T. B. Raji Krishna, D. Jayanthi, D.S. Shylu Sam, K. Kavitha, Naveen Kumar Maurya, “Application of machine learning techniques for churn prediction in the telecom business,” Results Eng., vol. 24, p. 103165, 2024, doi: https://doi.org/10.1016/j.rineng.2024.103165.

R. Seethalakshmi and B. S. Varsha, “Advancing Telecom Customer Churn using Deep Learning,” 8th Int. Conf. Electron. Commun. Aerosp. Technol. ICECA 2024 - Proc., pp. 1420–1427, 2024, doi: 10.1109/ICECA63461.2024.10801009.

“Telco Customer Churn.” Accessed: Jul. 26, 2025. [Online]. Available: https://www.kaggle.com/datasets/blastchar/telco-customer-churn

K. H. Victor Chang, “Prediction of Customer Churn Behavior in the Telecommunication Industry Using Machine Learning Models,” Algorithms, vol. 17, no. 6, p. 231, 2024, doi: https://doi.org/10.3390/a17060231.

H. K. T. Lewlisa Saha, “Deep Churn Prediction Method for Telecommunication Industry,” Sustainability, vol. 15, no. 5, p. 4543, 2023, doi: https://doi.org/10.3390/su15054543.

A. Thanam, M. S. Malchijah Raj, M. R. Joel, P. Shanthakumar, and J. J. Jacson, “Enhancing Telecom Customer Loyalty Through Churn Prediction Models,” 8th Int. Conf. Electron. Commun. Aerosp. Technol. ICECA 2024 - Proc., pp. 770–774, 2024, doi: 10.1109/ICECA63461.2024.10800923.

K. W. J. Rabih, R., Weifeng Sun, Majid Ayoubi, “Highly Accurate Customer Churn Prediction in the Telecommunications Industry Using MLP,” Int. J. Integr. Sci. Technol., vol. 2, no. 10, pp. 931–946, 2024, doi: https://doi.org/10.59890/ijist.v2i10.2564.

K. T. M. & M. A. A.-F. Shimaa Ouf, “A proposed hybrid framework to improve the accuracy of customer churn prediction in telecom industry,” J. Big Data Vol., vol. 11, no. 70, 2024, doi: https://doi.org/10.1186/s40537-024-00922-9.

S. R. Subaash, D. Nimma, B. K. Bala, S. A. Khan, M. Roy, and V. S. Rao, “Enhancing Customer Churn Prediction in Telecommunication with CNN-Gradient Boosting Machine,” 2024 Int. Conf. Intell. Comput. Sustain. Innov. Technol. IC-SIT 2024, 2024, doi: 10.1109/IC-SIT63503.2024.10862836.

M. R. Kumar, S. Priyanga, J. S. Anusha, V. Chatiyode, J. Santiago, and D. Chaudhary, “Enhancing Telecommunications Customer Retention: A Deep Learning Approach Using LSTM for Predictive Churn Analysis,” 2nd IEEE Int. Conf. Data Sci. Netw. Secur. ICDSNS 2024, 2024, doi: 10.1109/ICDSNS62112.2024.10691038.

M. E. & K. S. Irina V. Pustokhina, Denis A. Pustokhin, Phong Thanh Nguyen, “Multi-objective rain optimization algorithm with WELM model for customer churn prediction in telecommunication sector,” Complex Intell. Syst., vol. 9, pp. 3473–3485, 2023, doi: https://doi.org/10.1007/s40747-021-00353-6.

M. G. R. A. and A. T. S. Saha, C. Saha, M. M. Haque, “ChurnNet: Deep Learning Enhanced Customer Churn Prediction in Telecommunication Industry,” IEEE Access, vol. 12, pp. 4471–4484, 2024, doi: 10.1109/ACCESS.2024.3349950.

B. Demir and Ö. Ö. Ergün, “Customer Churn Prediction With Machine Learning Methods In Telecommunication Industry,” Res. Sq., Sep. 2023, doi: 10.21203/RS.3.RS-3343217/V1.

Y. Bharambe, P. Deshmukh, P. Karanjawane, D. Chaudhari, and N. M. Ranjan, “Churn Prediction in Telecommunication Industry,” 2023 Int. Conf. Adv. Technol. ICONAT 2023, 2023, doi: 10.1109/ICONAT57137.2023.10080425.

N. A. Hanan Abdullah Mengash, “Archimedes Optimization Algorithm-Based Feature Selection with Hybrid Deep-Learning-Based Churn Prediction in Telecom Industries,” Biomimetics, vol. 9, no. 1, p. 1, 2024, doi: https://doi.org/10.3390/biomimetics9010001.

F. Alhaqui, M. Elkhechafi, and A. Elkhadimi, “Machine learning for telecoms: From churn prediction to customer relationship management,” Proc. 2022 IEEE Int. Conf. Mach. Learn. Appl. Netw. Technol. ICMLANT 2022, 2022, doi: 10.1109/ICMLANT56191.2022.9996496.

R. Nkolele and H. Wang, “Explainable Machine Learning: A Manuscript on the Customer Churn in the Telecommunications Industry,” Conf. Proc. 2021 Ethics Explain. Responsible Data Sci. EE-RDS 2021, 2021, doi: 10.1109/EE-RDS53766.2021.9708561.