Explainable AI Dimensionality Reduction Techniques Based for Client Attrition Prediction

Benjamin Chiemeka Opara; Chinedu Callistus Olumba; Chinedu Franklin Elechi; Emmanuel Chiemena Anunobi; Felista Obianuju Anunobi; Ezealaji Osinachi Stanley; Chima Wisdom Olumba; Gladys Chinyere Olumba

doi:10.56201/ijefm.v11.no4.2026.pg57.111

Explainable AI Dimensionality Reduction Techniques Based for Client Attrition Prediction

Benjamin Chiemeka Opara, Chinedu Callistus Olumba, Chinedu Franklin Elechi, Emmanuel Chiemena Anunobi, Felista Obianuju Anunobi, Ezealaji Osinachi Stanley, Chima Wisdom Olumba, Gladys Chinyere Olumba

Abstract

In the financial field, predicting client churn is of great significance for banks to maintain profitability and reputation, and attract new customers. Traditional prediction methods, such as KNN and RF, typically assume linear relationships and struggle with complex linear patterns in customer behavior. Recent research has employed machine learning and dimensionality reduction techniques to improve prediction accuracy, but most studies have focused on a single model and lack a comprehensive analysis of how different dimensionality reduction methods interact with various classifiers. This study employed three dimensionality reduction techniques: Uniform Manifold Approximation and Projection , Neighbourhood Component Analysis , and Partial Least Squares Discriminant Analysis to combine 10 machine learning classifiers including SVM, KNN, logistic regression, etc., to conduct research on the prediction of credit card customer churn. The Bank Churners dataset was balanced by using SMOTE method. Additionally, each classifier is optimized using GridSearchCV and its performance is evaluated using key evaluation metrics. The combined use of the reduced dataset from NCA with the K-nearest neighbor classifier achieved the best performance, with an accuracy rate of 96.21% and a precision rate of 95.84%. Among all the dimensionality reduction methods, NCA achieved excellent results in most of the classifiers. This study systematically compared the three-dimensional reduction strategy and ten classifiers for credit card churn prediction. The research results emphasized that NCA and KNN formed an effective combination for building an accurate and interpretable churn prediction system. This study provides practical insights for financial institutions aiming to deploy efficient customer retention models. Keyword: Explainability, Machine learning, Customer attrition, Dimensionality reduction, Models, Financial.

References

F. F. Reichheld and W. E. Sasser, 'Zero defections: Quality comes to services,' Harv. Bus. Rev., vol. 68, no. 5, pp. 105–111, 1990. R. N. Bolton and T. M. Bronkhorst, 'The relationship between customer complaints to the firm and subsequent exit behavior,' ACR North Am. Adv., vol. 22, pp. 94–100, 1995. G. U. Nneji, J. Cai, J. Deng, M. A. Hossin, S. Nahar, and J. Jackson, “Identification of Diabetic Retinopathy Using Weighted Fusion Deep Learning Based on Dual-Channel Fundus Scans”, Diagnostics, vol. 12, no. 2, p. 540, Feb. 2022, https://doi.org/10.3390/diagnostics12020540. Li, X., Wang, Y., Monday, H.N. and Nneji, G.U., 2025. A novel residual learning of multi- scale feature extraction model for the classification of rice grain varieties. Computers and Electronics in Agriculture, 237, p.110491. Monday, H.N., Nneji, G.U., Hossin, M.A., Mark, K.D., Umana, E.S., Mgbejime, G.T. and Li, J., 2025. Enhancing ECG Classification in Cardiac Diagnostics: A Novel Approach Using Adaptive Focal Cross-Entropy Loss Function. IEEE Journal of Biomedical and Health Informatics. Nneji, G. U., Monday, H. N., Pathapati, V. S. R., Nahar, S., Mgbejime, G. T., Umana, E. S., & Hossin, M. A. (2025). FFS-IML: fusion-based statistical feature selection for machine learning-driven interpretability of chronic kidney disease. International Journal of Machine Learning and Cybernetics, 1-34. Nneji, G. U., Monday, H. N., Mgbejime, G. T., Pathapati, V. S. R., Nahar, S., & Ukwuoma, C. C. (2023). “Lightweight separable convolution network for breast cancer histopathological identification”. Diagnostics, 13(2), 299. https://doi.org/10.3390/diagnostics13020299 G. U. Nneji, J. Cai, J. Deng, H. N. Monday, E. C. James, and C. C. Ukwuoma, “Multi- Channel Based Image Processing Scheme for Pneumonia Identification”, Diagnostics, vol. 12, no. 2, p. 325, Jan. 2022, https://doi.org/10.3390/diagnostics12020325 C.-S. Lin, G.-H. Tzeng, and Y.-C. Chin, ‘Combined rough set theory and flow network graph to predict customer churn in credit card accounts’, Expert Systems with Applications, vol. 38, no. 1, pp. 8–15, Jan. 2011, doi: 10.1016/j.eswa.2010.05.039. Y. Xu, C. Rao, X. Xiao, and F. Hu, ‘Novel Early-Warning Model for Customer Churn of Credit Card Based on GSAIBAS-CatBoost’. B. Prabadevi, R. Shalini, and B. R. Kavitha, ‘Customer churning analysis using machine learning algorithms’, International Journal of Intelligent Networks, vol. 4, pp. 145– 154, 2023, doi: 10.1016/j.ijin.2023.05.005. F. Ö. Koçoğlu and T. Özcan, ‘A grid search optimized extreme learning machine approach for customer churn prediction’, Journal of Engineering Research, vol. 11, no. 3, pp. 103–112, Sept. 2023, doi: 10.36909/jer.16771. L. Geiler, S. Affeldt, and M. Nadif, ‘An effective strategy for churn prediction and customer profiling’, Data & Knowledge Engineering, vol. 142, p. 102100, Nov. 2022, doi: 10.1016/j.datak.2022.102100. M. Maduna, A. Telukdarie, I. Munien, U. Onkonkwo, and A. Vermeulen, ‘Smart Customer Churn Management System Using Machine Learning’, Procedia Computer Science, vol. 237, pp. 552–558, 2024, doi: 10.1016/j.procs.2024.05.139. P. Boozary, S. Sheykhan, H. GhorbanTanhaei, and C. Magazzino, ‘Enhancing customer retention with machine learning: A comparative analysis of ensemble models for accurate churn prediction’, International Journal of Information Management Data Insights, vol. 5, no. 1, p. 100331, June 2025, doi: 10.1016/j.jjimei.2025.100331. Z. Hu, F. Dong, J. Wu, and M. Misir, ‘Prediction of Banking Customer Churn Based on XGBoost with Feature Fusion’, in E-Business. New Challenges and Opportunities for Digital-Enabled Intelligent Future, vol. 517, Y. P. Tu and M. Chi, Eds, in Lecture Notes in Business Information Processing, vol. 517. , Cham: Springer Nature Switzerland, 2024, pp. 159–167. doi: 10.1007/978-3-031-60324-2_13. Mgbejime, G. T., Hossin, M. A., Nneji, G. U., Monday, H. N., & Ekong, F. (2022). “Parallelistic Convolution Neural Network Approach for Brain Tumor Diagnosis”. Diagnostics, 12(10), 2484. https://doi.org/10.3390/diagnostics12102484 Agbley, B. L. Y., Li, J., Hossin, M. A., Nneji, G. U., Jackson, J., Monday, H. N., & James, E. C. (2022). “Federated Learning-Based Detection of Invasive Carcinoma of No Special Type with Histopathological Images”. Diagnostics, 12(7), 1669. https://doi.org/10.3390/diagnostics12071669 Z. Hu, F. Dong, J. Wu, and M. Misir, ‘Prediction of Banking Customer Churn Based on XGBoost with Feature Fusion’, in E-Business. New Challenges and Opportunities for Digital-Enabled Intelligent Future, vol. 517, Y. P. Tu and M. Chi, Eds, in Lecture Notes in Business Information Processing, vol. 517. , Cham: Springer Nature Switzerland, 2024, pp. 159–167. doi: 10.1007/978-3-031-60324-2_13. A. Agnihotri and R. Saravanakumar, ‘Customer Retention in Banking: Utilizing AI and Machine Learning for Predictive Churn Analysis’, in 2025 3rd International Conference on Intelligent Systems, Advanced Computing and Communication , Silchar, India: IEEE, Feb. 2025, pp. 140–144. doi: 10.1109/ISACC65211.2025.10969188.

Explainable AI Dimensionality Reduction Techniques Based for Client Attrition Prediction

Abstract

References

More Articles from INTERNATIONAL JOURNAL OF ECONOMICS AND FINANCIAL MANAGEMENT