A Comprehensive Evaluation of Machine Learning and Deep Learning Models for Churn Prediction

Churn prediction has become one of the core concepts in customer relationship management within the insurances, telecom, and internet service provider industries, which is essential in customer retention. Therefore, this study attempts to analyze the effectiveness of the advanced machine learning an...

Full description

Saved in:
Bibliographic Details
Main Authors: Nabil M. AbdelAziz, Mostafa Bekheet, Ahmad Salah, Nissreen El-Saber, Wafaa T. AbdelMoneim
Format: Article
Language:English
Published: MDPI AG 2025-06-01
Series:Information
Subjects:
Online Access:https://www.mdpi.com/2078-2489/16/7/537
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849246512621551616
author Nabil M. AbdelAziz
Mostafa Bekheet
Ahmad Salah
Nissreen El-Saber
Wafaa T. AbdelMoneim
author_facet Nabil M. AbdelAziz
Mostafa Bekheet
Ahmad Salah
Nissreen El-Saber
Wafaa T. AbdelMoneim
author_sort Nabil M. AbdelAziz
collection DOAJ
description Churn prediction has become one of the core concepts in customer relationship management within the insurances, telecom, and internet service provider industries, which is essential in customer retention. Therefore, this study attempts to analyze the effectiveness of the advanced machine learning and deep learning models for churn prediction in the evaluation of the models’ performance across different sectors. This would help conclude whether the varied patterns of the churn throughout different sectors to the level that affects the model performance and to what extent. The work includes three datasets: namely, insurance churn, internet service provider customer churn, and Telecom churn datasets. The implementation and comparison conducted in this study of models include XGBoost, Convolutional Neural Networks (CNNs), and Ensemble Deep Learning with the pre-trained hybrid approach. The results show that the ensemble deep learning model outperforms other models in terms of accuracy and F1-score, achieving accuracies of up to 95.96% in the insurance churn dataset and of 98.42% in the telecom churn dataset. Moreover, traditional machine learning models like XGBoost also produced competitive results for selected datasets. The proposed deep learning ensembles reveal the strength and possibility for churn prediction and provide a benchmark for future research relevant to customer retention strategies. Also, the proposed ensemble deep learning model shows stable performance across different sectors, which reflects its ability to capture the varied churn patterns of different sectors.
format Article
id doaj-art-c641df83397947f594fa129cc7adb1ae
institution Kabale University
issn 2078-2489
language English
publishDate 2025-06-01
publisher MDPI AG
record_format Article
series Information
spelling doaj-art-c641df83397947f594fa129cc7adb1ae2025-08-20T03:58:29ZengMDPI AGInformation2078-24892025-06-0116753710.3390/info16070537A Comprehensive Evaluation of Machine Learning and Deep Learning Models for Churn PredictionNabil M. AbdelAziz0Mostafa Bekheet1Ahmad Salah2Nissreen El-Saber3Wafaa T. AbdelMoneim4Information Systems Department, Faculty of Computers and Informatics, Zagazig University, Zagazig 44519, EgyptInformation Systems Department, Faculty of Computers and Informatics, Zagazig University, Zagazig 44519, EgyptCollege of Computing and Information Sciences, University of Technology and Applied Sciences, Ibri P.O. Box 466, OmanInformation Systems Department, Faculty of Computers and Informatics, Zagazig University, Zagazig 44519, EgyptInformation Systems Department, Faculty of Computers and Informatics, Zagazig University, Zagazig 44519, EgyptChurn prediction has become one of the core concepts in customer relationship management within the insurances, telecom, and internet service provider industries, which is essential in customer retention. Therefore, this study attempts to analyze the effectiveness of the advanced machine learning and deep learning models for churn prediction in the evaluation of the models’ performance across different sectors. This would help conclude whether the varied patterns of the churn throughout different sectors to the level that affects the model performance and to what extent. The work includes three datasets: namely, insurance churn, internet service provider customer churn, and Telecom churn datasets. The implementation and comparison conducted in this study of models include XGBoost, Convolutional Neural Networks (CNNs), and Ensemble Deep Learning with the pre-trained hybrid approach. The results show that the ensemble deep learning model outperforms other models in terms of accuracy and F1-score, achieving accuracies of up to 95.96% in the insurance churn dataset and of 98.42% in the telecom churn dataset. Moreover, traditional machine learning models like XGBoost also produced competitive results for selected datasets. The proposed deep learning ensembles reveal the strength and possibility for churn prediction and provide a benchmark for future research relevant to customer retention strategies. Also, the proposed ensemble deep learning model shows stable performance across different sectors, which reflects its ability to capture the varied churn patterns of different sectors.https://www.mdpi.com/2078-2489/16/7/537churn predictioncustomer retentiondeep learningensemble learningmachine learning
spellingShingle Nabil M. AbdelAziz
Mostafa Bekheet
Ahmad Salah
Nissreen El-Saber
Wafaa T. AbdelMoneim
A Comprehensive Evaluation of Machine Learning and Deep Learning Models for Churn Prediction
Information
churn prediction
customer retention
deep learning
ensemble learning
machine learning
title A Comprehensive Evaluation of Machine Learning and Deep Learning Models for Churn Prediction
title_full A Comprehensive Evaluation of Machine Learning and Deep Learning Models for Churn Prediction
title_fullStr A Comprehensive Evaluation of Machine Learning and Deep Learning Models for Churn Prediction
title_full_unstemmed A Comprehensive Evaluation of Machine Learning and Deep Learning Models for Churn Prediction
title_short A Comprehensive Evaluation of Machine Learning and Deep Learning Models for Churn Prediction
title_sort comprehensive evaluation of machine learning and deep learning models for churn prediction
topic churn prediction
customer retention
deep learning
ensemble learning
machine learning
url https://www.mdpi.com/2078-2489/16/7/537
work_keys_str_mv AT nabilmabdelaziz acomprehensiveevaluationofmachinelearninganddeeplearningmodelsforchurnprediction
AT mostafabekheet acomprehensiveevaluationofmachinelearninganddeeplearningmodelsforchurnprediction
AT ahmadsalah acomprehensiveevaluationofmachinelearninganddeeplearningmodelsforchurnprediction
AT nissreenelsaber acomprehensiveevaluationofmachinelearninganddeeplearningmodelsforchurnprediction
AT wafaatabdelmoneim acomprehensiveevaluationofmachinelearninganddeeplearningmodelsforchurnprediction
AT nabilmabdelaziz comprehensiveevaluationofmachinelearninganddeeplearningmodelsforchurnprediction
AT mostafabekheet comprehensiveevaluationofmachinelearninganddeeplearningmodelsforchurnprediction
AT ahmadsalah comprehensiveevaluationofmachinelearninganddeeplearningmodelsforchurnprediction
AT nissreenelsaber comprehensiveevaluationofmachinelearninganddeeplearningmodelsforchurnprediction
AT wafaatabdelmoneim comprehensiveevaluationofmachinelearninganddeeplearningmodelsforchurnprediction