EUVIMEDEUVIMED entdecken
Crossref

Customer Churn Analysis and Prediction Using Machine Learning for Telecom Services

Prof. Kanifnath S Satav, Aniruddha R Ughade

International Scientific Journal of Engineering and Management · 19.04.2026 · 05 (04) · 1-5

DOI: 10.55041/isjem06537 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Scientific Journal of Engineering and Management, online erschienen am 19.04.2026. Verfasst von Prof. Kanifnath S Satav und 1 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Customer retention has become a key concern for telecom service providers as competition continues to intensify and customers gain more flexibility to switch between providers. Unlike earlier markets where customer loyalty was relatively stable, today’s telecom users often change services based on pricing, service quality, and perceived value. This behaviour directly impacts revenue and increases the cost of acquiring new customers. In the context, understanding the factors that drive customer churn is essential for building effective retention strategies. In this study, we attempt to understand why customers leave telecom services using a telecom dataset that includes demographic details, service usage patterns, and billing information. The approach combines data preprocessing, exploratory analysis, and the application of machine learning techniques to identify customer who are more likely to discontinue services. Models such as Decision Tree, Random Forest, and XGBoost were implemented and evaluated to understand their effectiveness in classification tasks. Since the dataset exhibited class imbalance, SMOTE was applied to improve model learning and ensure better representation of churn cases. The result shows that ensemble models perform more consistently compared to individual models, with XGBoost providing the most reliable outcomes after tuning. Factors such as contract type, tenure, and monthly charges were found to play a significant role in influencing churn behaviour. These insights can help telecom companies take proactive steps toward improving customer retention. Overall, the study highlights the role of data-driven decision-making in reducing churn and improving customer retention. Key Words: Customer Churn, Telecom Analytics, Machine Learning, Customer Retention.

Zitieren

APA

Satav, P. K. S., & Ughade, A. R. (2026). Customer Churn Analysis and Prediction Using Machine Learning for Telecom Services. International Scientific Journal of Engineering and Management, 05(04), 1-5. https://doi.org/10.55041/isjem06537

Vancouver

Satav PKS, Ughade AR. Customer Churn Analysis and Prediction Using Machine Learning for Telecom Services. International Scientific Journal of Engineering and Management. 2026;05(04):1-5. doi:10.55041/isjem06537

BibTeX
@article{Satav2026,
  author = {Satav, Prof. Kanifnath S and Ughade, Aniruddha R},
  title = {Customer Churn Analysis and Prediction Using Machine Learning for Telecom Services},
  journal = {International Scientific Journal of Engineering and Management},
  year = {2026},
  volume = {05},
  number = {04},
  pages = {1--5},
  doi = {10.55041/isjem06537}
}
Kostenlos starten →