International Journal of Research and Innovation in Applied Science (IJRIAS) |Volume VII, Issue X, October 2022|ISSN 2454-6194
A Comparative Analysis of The Performance of Homogenous Ensembles on Customer Churn Prediction
Ramoni Tirimisiyu Amosa, Fabiyi Aderanti Alifat, Olorunlomerue Adam Biodun, Oluwatosin Adefunke Oluwatobi & Ugwu Jennifer Ifeoma
Computer Science Department, Federal Polytechnic Ede, Osun State, Nigeria
Customer retention is a challenging and critical issue in telecommunication and service-based sectors. Various researchers have established the need for a service-based company to retain their existing customers much cheaper than acquiring new ones. However, the predictive models for observing customers’ behavior is one of the great instruments in the customer retention process and inferring the future behavior of the customers. Selecting the right and best model is another herculean task because the performances of predictive models are greatly affected when the real-world dataset is highly imbalanced. The study analyses the performance of homogeneous ensembles; bagging, boosting, rotation forest, cascade, and dagging. These ensembles were applied to both raw and balanced datasets to compare the performance of the models. The data sampling method (oversampling) was adopted to balance the raw dataset. The primary metric used for the evaluation of the performance of the models was Accuracy and ROC/AUC (Receiver Operating Characteristics/Area Under Curve). Weka 3.8.5 machine learning tool used to analyze and develop the models. The study reveals that Bagging had the best performance having an AUC of 0.987, followed by boosting and Rotation Forest both with an AUC of 0.985.
Keywords: Customer, Dataset, Ensemble, Homogeneous, Model.
I. INTRODUCTION
Due to dominance of mobile communication in telecommunication sector, new ideas, technologies and players are emerging daily and this has made it necessary and important to predict the customers and client who may have to shift from one service provider to a new one. Churn occur when a customer leave a service provider and move to the new service provider, in certain situation customer churn is also refers to as customer attrition. If a customer switches a service provider’s company then face loss occurs in the company’s revenue. Prediction can be performed to identify the potential churners and retention solutions may be provided to them (Bilal et al., 2022). A large number of mining algorithms are available which classify the behavior of customers into churner and non-churners.
The telecommunication sector is one of the major source of revenue and very crucial to the economy development in developed countries for almost two decades (Ullah et al., 2019; Adnan, 2021). Data mining plays a vital role for prediction and analysis in the telecom industry due to