What type of study is this?

This is a Quantitative Study study.

October 2, 2025Open Access

Comparing Traditional Machine Learning and Advanced Gradient Boosting Techniques in Customer Churn Prediction: A Telecom Industry Case Study

Key Points

Advanced gradient boosting methods like LightGBM achieved an F1-score of 92% in customer churn prediction, outpacing traditional models.
The effectiveness of various models was evaluated using metrics such as Precision, Recall, F1-score, and ROC AUC.
This research involved examining multiple machine learning models in a comprehensive analysis focused on the telecom industry.
Findings highlight the advantages of sophisticated models in addressing the challenges posed by imbalanced datasets.

Abstract

In this study, a range of machine learning models, including Artificial Neural Networks, Decision Trees, Support Vector Machines, Random Forests, Logistic Regression, and advanced gradient boosting methods (XGBoost, LightGBM, and CatBoost), were examined for their efficacy in predicting customer churn within the telecommunications industry. The research utilized a publicly accessible dataset for this purpose. The effectiveness of these models was measured using established evaluation metrics such as Precision, Recall, F1-score, and the Receiver Operating Characteristic Area Under Curve (ROC AUC). The research findings emphasize the efficiency of boosting algorithms in managing the complex aspects of predicting customer churn. In particular, LightGBM was remarkable, securing an outstanding F1-score of 92% and an ROC AUC of 91%. These figures greatly exceed the performance of conventional models such as Decision Trees and Logistic Regression. This highlights the superiority of sophisticated machine learning methods in dealing with challenges posed by imbalanced datasets and complex interrelations among features.

اسأل الذكاء الاصطناعي

Bookmark

View Full Paper