Customer Churn Prediction Using Weight Average Ensemble Machine Learning Model

The main purpose of this study is to build a framework with several combinations of preprocessing techniques and an ensemble of two machine learning models, XGBoost and random forest. The dataset for this study is from a public dataset platform; the experiment uses two different sectors: telecom and insurance

ML Framework

Two differents dataset preprocessed by filling missing value and SMOTE. After the preprocessing finished, ensemble machine learning did a classification task for churn prediction

The Result

• Telecom dataset : F1-Score (0.850)
• Insurance dataset : F1-Score (0.947)

Publication

This works was presented on International Joint Conference on Computer Science and Software Engineering (JCSSE) 2022 in Phitsanulok, Thailand
Read the full publication here : https://ieeexplore.ieee.org/abstract/document/10202105

Acknowledgments

Thanks to Khon Kaen University for Funding this research work.