Optimizing Customer Retention in Banking Through Advanced AI Technologies

Main Article Content

Joby Jacob, E. J Thomson Fredrik

Abstract

This research presents this project, which explores how advanced AI technologies can help optimize customer retention in banking. Customer churn is predicted using historical data using machine learning models such as Random Forest, XGBoost, SVM, Gradient Boosting, KNN, and Naive Bayes respectively. Unlike typical methods of segmentation, in K-means clustering the data is partitioned based on customer behaviour and thus personalized retention strategies are possible. The metrics such as accuracy, precision-recall and F1 score demonstrate that Gradient Boosting performs better than other algorithms. This finding underscores its importance to predictive analytics and to customer segmentation in the banking sector to improve loyalty and reduce churn.

Article Details

Section
Articles