What question did this study set out to answer?

The research aims to analyze customer behavior and predict churn in banking institutions using analytics.

April 19, 2026Open Access

Customer Engagement And Retention Utilization Analytics For Retention Strategy

Key Points

The research aims to analyze customer behavior and predict churn in banking institutions using analytics.
Conducted exploratory data analysis (EDA) to identify customer patterns.
Applied various machine learning models to predict customer churn.
Utilized XGBoost for prediction, achieving high accuracy.
Developed an interactive Streamlit dashboard to visualize insights.
Achieved approximately 87% accuracy with the XGBoost model.
Obtained a ROC-AUC score of 0.86, indicating strong model performance.

Abstract

Customer churn is one of the major challenges faced by banking institutions as it directly impacts profitability and long-term customer relationships. This research focuses on analysing customer behaviour and predicting churn using machine learning techniques. Exploratory Data Analysis (EDA) was performed to identify patterns related to customer engagement, product usage, and financial activity. Among various models, XGBoost achieved strong performance with an accuarcy of approximately 87% and ROC-AUC score of 0.86. An interactive Streamlit dashboard was developed to visualize insights and support decision-making.

Customer Engagement And Retention Utilization Analytics For Retention Strategy

Key Points

Abstract

Cite This Study