An Integrated AI-Driven Framework for Customer Churn Prediction and Behavioural Analytics in Telecommunications
Nature Journal of Emerging Sciences Technologies and Innovations · 29.04.2026 · 7 (4) · 337-347
DOI: 10.65752/n4ch1084 ↗Kurz gefasst
Fachartikel in der Zeitschrift Nature Journal of Emerging Sciences Technologies and Innovations, online erschienen am 29.04.2026. Verfasst von Lilian Chisom Charles Opara und 2 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Customer churn poses a significant challenge to the telecommunications industry due to its impact on revenue stability and retention costs, particularly in highly competitive and prepaid-dominated markets such as Nigeria. This study develops an artificial intelligence-based analytical framework that integrates customer churn prediction and behavioural segmentation using a real-world telecom dataset comprising 2,850 unique subscribers after data cleaning. Multiple machine learning models, including Logistic Regression, Decision Tree, Random Forest, Support Vector Machine, K-Nearest Neighbour, Gradient Boosting Machine and Extreme Gradient Boosting (XGBoost), were implemented under a CRISP-DM pipeline incorporating preprocessing, feature engineering and class imbalance handling. Model performance was evaluated using stratified cross-validation and assessed with accuracy, precision, recall, F1-score and AUC–ROC metrics. Among the evaluated models, XGBoost achieved the strongest predictive performance, with an accuracy of 93.97% and an AUC of 0.98. Behavioural segmentation using K-means clustering identified eight customer segments, with cluster validity assessed using a silhouette coefficient of 0.299, indicating moderate but meaningful behavioural structure. The integration of churn prediction and segmentation enables differentiated retention strategies aligned with customer engagement patterns. A key limitation of this study is the reliance on a single telecom dataset, which may constrain generalisability across operators. Overall, the findings demonstrate the practical value of combining predictive modelling and behavioural analytics to support data-driven churn management in emerging telecommunications markets.
Zitieren
APA
Opara, L. C. C., Ikegwu, A. C., & Igwe, S. A. (2026). An Integrated AI-Driven Framework for Customer Churn Prediction and Behavioural Analytics in Telecommunications. Nature Journal of Emerging Sciences Technologies and Innovations, 7(4), 337-347. https://doi.org/10.65752/n4ch1084
Vancouver
Opara LCC, Ikegwu AC, Igwe SA. An Integrated AI-Driven Framework for Customer Churn Prediction and Behavioural Analytics in Telecommunications. Nature Journal of Emerging Sciences Technologies and Innovations. 2026;7(4):337-347. doi:10.65752/n4ch1084
BibTeX
@article{Opara2026,
author = {Opara, Lilian Chisom Charles and Ikegwu, Anayo Chukwu and Igwe, Sylvester Agbo},
title = {An Integrated AI-Driven Framework for Customer Churn Prediction and Behavioural Analytics in Telecommunications},
journal = {Nature Journal of Emerging Sciences Technologies and Innovations},
year = {2026},
volume = {7},
number = {4},
pages = {337--347},
doi = {10.65752/n4ch1084}
}
EUVIMED