This applied data analytics research paper presents a dashboard-supported banking retention study focused on customer engagement, product utilization, high-value disengagement, and relationship strength scoring. The study analyzes a customer-level banking churn dataset using engagement classification, product-depth segmentation, high-value customer detection, KPI measurement, and retention-strength scoring. The research reframes churn as a behavioral relationship-strength problem rather than only a demographic or financial-value issue. Key dashboard findings show that the baseline customer base includes 10,000 customers, with 7,963 retained customers and 2,037 churned customers. Inactive Members contribute 63.9% of total churn, while Active Members show stronger retention quality. Product-depth analysis identifies two-product customers as the strongest retention segment, with 92.42% retention. The high-value customer detector identifies 4,351 high-value customers, including 2,154 high-value disengaged customers, producing a High-Balance Disengagement Rate of 49.51% and balance exposure of 232,942,972. The research also evaluates retention strength scoring. Critical Retention Risk customers show 69.0% churn, while Very Strong Retention customers show 0.0% churn. These results support targeted retention actions such as inactive-member reactivation, premium-customer recovery, product-bundling optimization, and retention-tier based campaign prioritization. The paper is intended for applied analytics portfolio documentation, research repository publication, and professional data analytics project submission.
Mohit Gupta (Sat,) studied this question.