A cross-border community for researchers with openness, equality and inclusion
Join USS Create Account Sign In
Join USS Create Account Sign In

ABSTRACT LIBRARY

Home / USS Digital Library / Article / Details

CUSTOMER CHURN PREDICTION USING ML MODELS

Publisher: IEEE

Authors: Moazzam Abeer, School of Computing, Skyline University College, P.O. Box 1797, Sharjah, UAE Rahimi Muzhda, School of Computing, Skyline University College, P.O. Box 1797, Sharjah, UAEAlomoush Waleed, Plekhanov Russian University of Economics in Dubai.； Dubai Knowledge Park； Dubai； UAE Alrosan Ayat, Artificial Intelligence Center for Humanities and social science research, Alwasl University, Dubai, UAE Khashan Osama A, Research and Innovation Centers, Rabdan Academy, Abu Dhabi, P.O. Box 114646, United Arab Emirates Che muda Zakaria, INTI-IU University

  • Favorite
  • Share:

Abstract:

Predicting customer churn is an essential part of retention strategy for telecom companies so as to maximize revenue. In this paper, four machine learning models, Random Forest, Gradient Boosting, Logistic Regression, and K-Nearest Neighbors are compared to predict customer churn using a telecom dataset. We use SMOTE-Tomek to cope with class imbalance and optimize models by using GridSearchCV, Optuna, and Grey Wolf Optimizer. Our optimized Random Forest has 85.9% of accuracy beating other models. The study reveals the main churn factors such as type of contract and the usage of services, which are useful in developing targeted retention strategies for telecom providers..

Keywords: Customer churn, machine learning, Random Forest, SMOTE, hyperparameter optimization

Published in: 2024 Asian Conference on Communication and Networks (ASIANComNet)

Date of Publication: --

DOI: -

Publisher: IEEE

请输入有效的邮箱地址
© Copyright 2024 USS - the United Societies of Science - All rights reserved. The USS website is developed and maintained by BoomSCI limited.