Ensembled Learning Based Model for Bank Churn Prediction

Jieyuan Deng, Junda Huang, Dongliang Liu, Shaohan Yang

2024

Abstract

Predicting customer churn rate helps banks retain customers, stabilize their market position, and improve services, providing a better customer experience for both parties, especially for developed countries. Although various scholars have conducted different studies in various locations, there has been no rigorous research on predicting bank customer churn. The purpose of this study is to develop a satisfactory predictive model to forecast the probability of customer churn for banks, providing reliable references for numerous banks. This paper implements various machine learning methods and deep learning models, including Logistic Regression, Random Forest, Neural Network, XGBoost, Decision Tree, Gradient Boosting, and Ada Boost. Among all models, the combination of Random Forest and Neural Network achieved the best results, with an adjusted recall1 of 0.6 and precision0 of 0.9. In addition, we used insights obtained from these powerful ensemble learning models to analyze factors leading to bank customer churn.

Paper Citation

in Harvard Style

Deng J., Huang J., Liu D. and Yang S. (2024). Ensembled Learning Based Model for Bank Churn Prediction. In Proceedings of the 1st International Conference on Engineering Management, Information Technology and Intelligence - Volume 1: EMITI; ISBN 978-989-758-713-9, SciTePress, pages 10-15. DOI: 10.5220/0012887100004508

in Bibtex Style

@conference{emiti24,
author={Jieyuan Deng and Junda Huang and Dongliang Liu and Shaohan Yang},
title={Ensembled Learning Based Model for Bank Churn Prediction},
booktitle={Proceedings of the 1st International Conference on Engineering Management, Information Technology and Intelligence - Volume 1: EMITI},
year={2024},
pages={10-15},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012887100004508},
isbn={978-989-758-713-9},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 1st International Conference on Engineering Management, Information Technology and Intelligence - Volume 1: EMITI
TI - Ensembled Learning Based Model for Bank Churn Prediction
SN - 978-989-758-713-9
AU - Deng J.
AU - Huang J.
AU - Liu D.
AU - Yang S.
PY - 2024
SP - 10
EP - 15
DO - 10.5220/0012887100004508
PB - SciTePress