Customer Churn Prediction for Imbalanced Class Distribution of Data in Business Sector
DOI:
https://doi.org/10.3126/jacem.v5i0.26693Keywords:
Churn Prediction, Machine Learning, Business Intelligence, CRM, Telecommunication, Class Imbalance, Problem, Naïve Bayes, Logistic Regression, XGBoost, Random ForestAbstract
Churners are those people who are about to transfer their business to a competitor or simply who cancel a subscription to a service. This paper is based on a specific business sector, which is telecommunication sector. With a churn rate of 30%, the telecommunication sector takes the first place on the list. In this paper, we present some advanced data mining methodologies which predicts customer churn in the pre-paid mobile telecommunications industry using a call detail records dataset. To implement the predictive models, we initially propose and then apply four machine learning algorithms: Random Forest, Naïve Bayes, Logistic Regression, and XG Boost. To evaluate the models, we use various evaluation metrics and find the best model which will be suitable for any class imbalanced data and also our business case. This paper can also be viewed as a comparative study on the most popular machine learning methods applied to the challenging problem of customer churn prediction.
Downloads
Downloads
Published
How to Cite
Issue
Section
License
JACEM reserves the copyright for the published papers. Author will have right to use content of the published paper in part or in full for their own work.