Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM66056
Volume:
10 |
7 |
Jul 2026
Pages:
1-16
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.
Faculty of computing and IT
GM University
Faculty of computing and IT
GM University
Faculty of computing and IT
GM University
Faculty of computing and IT
GM University
Faculty of computing and IT
GM University
Faculty of computing and IT
GM University
The importance of customer churn prediction cannot be overstated since it has a vested role in enabling businesses to retain their customers while reducing the loss of revenue owing to stiff competition. The paper puts forth a machine learning-based customer churn prediction methodology that can help firms foresee the customers who are likely to leave the service provider. For this purpose, the IBM Telco Customer Churn Dataset was used, comprising a total of 7,041 records documenting several facets of customer data such as the demographics, service used, billing information, and churn status. To achieve maximum efficiency of the collected data related to customers and the accuracy of the conclusions reached through it, a structured data preprocessing pipeline that includes missing value treatment, feature encoding, feature scaling, and train-test split was used. Employing six methods of supervised machine learning, the author evaluated the performance of the models used based on the values of accuracy, precision, recall, F-Score, ROC-AUC, and others. In order to make the model less complex and more interpretable, the SHAP approach was also implemented in the study to study the impact of the independent variables on the result. As an outcome of this research, it has been established that among all the models LightGBM gave the most promising results. The suggested structure provides an effective practical solution in terms of predicting customer churn, enabling companies to apply proactive measures of customer retention, substantiate their decisions, and ensure enhanced sustainability of their business.
KEYWORDS
This study laid out an advanced framework for predicting customer churn through machine learning. Six algorithms were compared in this study, including logistic regression, decision tree, random forest, support vector machine (SVM), XGBoost, and LightGBM using the IBM Telco Customer Churn Dataset. In this study, the LightGBM algorithm outperforms in terms of accuracy, efficiency, and reliability. In addition to this, the integration of SHapley Additive exPlanations (SHAP) enables us to understand the underlying factors for customer churn. The introduction of a Flask web application also allows us to showcase the real-life implications of the framework. Thus, the results of this research show that the framework demonstrates great potential in the area of customer churn prediction processes.
[1] A. Sikri, R. Sharma, and P. Gupta, "Improving Customer Retention in Telecom Using Machine Learning-Based Churn Prediction," International Journal of Intelligent Systems and Applications in Engineering, vol. 12, no. 4, pp. 1256–1268, 2024. [2] Y. Suh, "Machine Learning-Based Customer Churn Prediction in Home Appliance Rental Business," Applied Sciences, vol. 13, no. 15, pp. 1–18, 2023. [3] V. Chang, H. Alenezi, and M. Ramachandran, "Customer Churn Prediction in the Telecommunication Industry Based on Machine Learning Models," IEEE Access, vol. 12, pp. 32584–32601, 2024. [4] M. AbdelAziz, A. Hassan, and S. Ibrahim, "Comparison of Machine Learning and Deep Learning Models for Customer Churn Prediction," Expert Systems with Applications, vol. 256, pp. 1–18, 2025. [5] R. Bhuria, A. Verma, and P. Singh, "Ensemble Approach to Customer Churn Prediction Using Machine Learning Techniques," Journal of King Saud University – Computer and Information Sciences, vol. 37, no. 2, pp. 102345, 2025. [6] M. Imani, H. Rahimi, and S. Mohammadi, "Customer Churn Prediction: A Systematic Literature Review," Artificial Intelligence Review, vol. 58, no. 3, pp. 1–39, 2025. References: [7] M. Abdelhady, A. El-Sayed, and M. Salem, “Utilizing Artificial Intelligence for Predictive Customer Churn Modeling,” Journal of Big Data. vol. 12, no.1, pp. 45-63, 2025. [8] R. Agrawal, S. Gupta, and V. Sharma, “Hybrid SMOTE and GAN-Based Customer Churn Prediction Using LightGBM,” IEEE Access, vol. 14, pp. 21456-21473, 2026. [9] A. El Attar, M. Hassan, and H. Ibrahim, “Explainable AI-Driven Customer Churn Prediction Using Ensemble Learning,” Expert Systems with Applications, vol. 271, pp. 126845, 2026. [10] J. Maan and P. Kaur, “Customer Churn Prediction Model Using Explainable Machine Learning Techniques,” International Journal of Information Management Data Insights, vol. 3, no. 2 pp. 100210, 2023.
Publication Date
7/14/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
0
Total views since publication
PDF Downloads
8
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...