Customer Churn Prediction Model Using Artificial Neural Networks (ANN): A Case Study in Banking
Baby, B., Dawod, Z., Sharif, S. and Elmedany, W. 2023. Customer Churn Prediction Model Using Artificial Neural Networks (ANN): A Case Study in Banking. 3ICT 2023: International Conference on Innovation and Intelligence for Informatics, Computing, and Technologies. University of Bahrain, Bahrain 20 - 21 Nov 2023 IEEE.
|Authors||Baby, B., Dawod, Z., Sharif, S. and Elmedany, W.|
Customer Churn has a great impact on banking industries as it accelerates a loss of revenue and customer loyalty. The focus of the research is to create a model for the banking sector using Artificial Neural Networks (ANNs) which can predict if the customer will churn. The prediction is based on the input features and the independent variable of the trained dataset. The hyperparameters are altered during model training using the forward propagation algorithm and cross-validation techniques which enable the model to perform well with respect to accuracy and precision rate. The achieved results illustrate that the suggested model has an accuracy of 86% at predicting customer attrition. In comparison to the logistic regression model outcomes, ANN models are more effective for predicting customer churn in the banking industry. The study suggests vital perceptions of how to employ machine learning approaches to increase client retention and decrease customer churn. Banks can use this model to spot clients who are at risk of churning and take proactive measures to keep them.
|Conference||3ICT 2023: International Conference on Innovation and Intelligence for Informatics, Computing, and Technologies|
|Accepted author manuscript|
File Access Level
|Publication process dates|
|Accepted||14 Sep 2023|
|Deposited||25 Sep 2023|
|Journal citation||In Press|
|Copyright holder||© 2023, IEEE|
|Copyright information||Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.|
11views this month
4downloads this month