Reducing Model Complexity in Bank Customer Churn Prediction Using Dimensionality Reduction and Explainable Machine Learning

Prisca Chimezie Opara; Sunday Chukwuebuka Uduogu; Merit Chinonso Opara; Nzubechi Augustine Oriaku; Adebusuyi Samuel Owoade; Uchechi Joyce Nneji; Benjamin Chiemeka Opara; Daniel Agbonifo

doi:10.56201/ijbfr.vol.12.no2.2026.pg48.85

Reducing Model Complexity in Bank Customer Churn Prediction Using Dimensionality Reduction and Explainable Machine Learning

Prisca Chimezie Opara, Sunday Chukwuebuka Uduogu,, Merit Chinonso Opara, Nzubechi Augustine Oriaku, Adebusuyi Samuel Owoade, Uchechi Joyce Nneji, Benjamin Chiemeka Opara, Daniel Agbonifo

Abstract

Customer churn poses significant challenges to banking profitability, with acquiring new customers costing 5-7 times more than retaining existing ones. Traditional statistical methods struggle with high-dimensional data and complex non-linear patterns. This study addresses these limitations by integrating advanced dimensionality reduction techniques with optimized machine learning to achieve accurate, interpretable churn prediction. Three dimensionality reduction techniques—UMAP, NCA, and PLSDA—were evaluated using a 10,000-customer European banking dataset across ten machine learning classifiers: SVM, Logistic Regression, KNN, Gaussian Naive Bayes, Decision Tree, Random Forest, AdaBoost, Bagging, Stacking, and Voting. Data preprocessing included SMOTE balancing, StandardScaler normalization, and one-hot encoding. GridSearchCV optimized hyper parameters systematically. Dual evaluation employed 80-20 train-test split and 10-fold cross-validation. SHAP framework provided comprehensive explainability through five visualization techniques. PLSDA emerged as the superior approach, achieving 84.68% accuracy with Random Forest using 8 features—20% dimensionality reduction while retaining 99% performance. Cross-validation confirmed robustness: 85.27 ± 0.50% accuracy, 92.79 ± 0.70% ROC-AUC. Ensemble methods outperformed single classifiers consistently. SHAP analysis identified Age, Number of Products, and Balance as dominant churn drivers. This study demonstrates that PLSDA-optimized machine learning achieves competitive accuracy with reduced computational complexity and enhanced interpretability. The framework provides actionable insights for targeted retention strategies while meeting regulatory compliance requirements for practical banking implementations.

Keywords

Customer Chun PredictionDimensionality ReductionPartial Least Squares Discriminant Analysis [PLSDA]Ensemble Machine LearningBanking AnalyticsModel Interpretability

References

Singh, P. P., Anik, F. I., Senapati, R., Sinha, A., Sakib, N., & Hossain, E. (2024). Investigating customer churn in banking: A machine learning approach and visualization app for data science and management. Data Science and Management, 7, 7–16. https://doi.org/10.1016/j.dsm.2023.09.002 Maduna, M., Telukdarie, A., Munien, I., Onkonkwo, U., & Vermeulen, A. (2024). Smart customer churn management system using machine learning. Procedia Computer Science, 237, 552–558. https://doi.org/10.1016/j.procs.2024.05.139 V?duva, A.-G., Oprea, S.-V., Niculae, A.-M., Bâra, A., & Andreescu, A.-I. (2024). Improving churn detection in the banking sector: A machine learning approach with probability calibration techniques. Electronics, 13(22), Article 4527. https://doi.org/10.3390/electronics13224527 Irawan, M. I., Putris, N. A. D., & Muhammad, N. (2024). Customer churn prediction using the RFM approach and extreme gradient boosting for company strategy recommendation. Register: Jurnal Ilmiah Teknologi Sistem Informasi, 10(2), 127–140. https://doi.org/10.26594/register.v10i2.4004 Du, S. (2024). Bank churn prediction using random forest and logistic regression. In Proceedings of the 2024 2nd International Conference on Finance, Trade and Business Management (FTBM 2024) (pp. 1–7). https://doi.org/10.2991/978-94-6463-546-1_2 Tran, H., Le, N., & Nguyen, V.-H. (2023). Customer churn prediction in the banking sector using machine learning-based classification models. Interdisciplinary Journal of Information, Knowledge, and Management, 18, 87–105. https://doi.org/10.28945/5086 N. T. N., & Pramod, D. (2025). Improving bank customer churn prediction with feature reduction using GA. Scientific Reports, 15, Article 40035. https://doi.org/10.1038/s41598-025-23867-2 Trinh, T. B., Vu, V. H., & Nguyen, T. V. (2025). A multi-task test case optimization framework with integrated explainable AI for customer churn prediction. The Journal of Supercomputing, 81, Article 1326. https://doi.org/10.1007/s11227-025-07816-4 Talaat, F. M., & Aljadani, A. (2025). AI-driven churn prediction in subscription services: Addressing economic metrics, data transparency, and customer interdependence. Neural Computing and Applications, 37, 8651–8676. https://doi.org/10.1007/s00521-025-11027- 6 Bhuria, R., Gupta, S., Kaur, U., Bharany, S., Rehman, A. U., Hussen, S., Tejani, G. G., & Jangir, P. (2025). Ensemble-based customer churn prediction in banking: A voting classifier approach for improved client retention using demographic and behavioral data. Discover Sustainability, 6, Article 28. https://doi.org/10.1007/s43621-025-00807-8 Vu, V.-H. (2024). Predict customer churn using combination deep learning networks model. Neural Computing and Applications, 36, 4867–4883. https://doi.org/10.1007/s00521- 023-09327-w Zhang, H., Wang, Y., Li, Z., & Wang, X. (2025). Machine learning models for bank customer churn prediction: A comparative study of LightGBM, CatBoost, and XGBoost. In Proceedings of the 2025 International Conference on Big Data, Artificial Intelligence and Digital Economy (BDAIE 2025) (pp. 1–11). https://doi.org/10.1145/3767052.3767054

Reducing Model Complexity in Bank Customer Churn Prediction Using Dimensionality Reduction and Explainable Machine Learning

Abstract

Keywords

References

More Articles from IIARD INTERNATIONAL JOURNAL OF BANKING AND FINANCE RESEARCH