article · المجلة الدولية للعلوم والتكنولوجيا
Customer churn poses a major challenge in banking, where acquiring new clients costs far more than retaining existing ones. Standard predictive models often rely on static demographic details, overlooking dynamic behavioral shifts that signal account abandonment. By creating four new behavioral markers, specifically the Balance-to-Salary Ratio, Product Utilization Index, Tenure-to-Age Ratio, and Credit Score Stability, churn prediction can be considerably enhanced. Evaluated on a retail banking dataset using SMOTE-Tomek to handle class imbalance, a TensorFlow-based Artificial Neural Network outperformed traditional ensemble methods like XGBoost and Random Forest. This neural network reached an accuracy of 89.7 percent and an F1-score of 0.77, marking a 15 percent boost over baseline models. Further analysis confirmed that these engineered behavioral metrics exerted greater influence on predictions than conventional demographic attributes, offering institutions a proactive mechanism to spot early attrition signals.
Retaining existing banking clients is far less costly than recruiting new ones. By identifying subtle shifts in customer behaviour rather than depending on basic demographic records, financial institutions can detect early warning signs of departure. This allows banks to intervene with timely retention strategies before accounts are abandoned, helping to safeguard customer relationships and reduce overall operational costs.
This predictive framework targets retail banks seeking to reduce client attrition. Because the model was developed and tested on an open Kaggle dataset rather than deployed in live banking infrastructure, it represents applied and tested research at an intermediate stage. Commercial adoption would require integrating these behavioral feature engineering pipelines into a bank's active transactional systems to generate real-time churn alerts for customer relationship teams.
AI-generated from the published abstract. Always read the original work before citing.
Customer churn remains a critical challenge for the global banking sector, where the cost of acquiring new clients significantly exceeds the cost of retaining existing ones. While machine learning has been widely adopted for churn prediction, existing models often rely on static demographic data, failing to capture the dynamic, “silent” behavioral shifts that precede account abandonment. This study aims to enhance churn prediction accuracy by introducing novel behavioral features and advanced feature engineering techniques. Utilizing a comprehensive retail banking dataset which downloaded from Kaggle, we engineered four unique behavioral markers: the Balance-to-Salary Ratio (BSR), Product Utilization Index (PUI), Tenure-to-Age Ratio (TAR), and Credit Score Stability (CSS). A comparative analysis was conducted between traditional ensemble methods (XGBoost, Random Forest) and a deep learning framework using a TensorFlow-based Artificial Neural Network (ANN). To address class imbalance, the SMOTE-Tomek integration technique was employed during preprocessing. Experimental results demonstrate that the inclusion of novel behavioral features significantly improved model performance. The TensorFlow ANN achieved the highest predictive power with an accuracy of 89.7% and an F1-Score of 0.77, representing a 15% improvement over baseline models. SHAP analysis confirmed that engineered behavioral ratios were more influential than traditional demographic variables. This research highlights that the “input space” (feature engineering) is as vital as the “model space” in financial analytics. The proposed framework provides banks with a proactive tool to detect subtle attrition signals, enabling more effective customer retention strategies.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.65723/rmsp2493
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
