Optimizing Customer Segmentation in the Banking Sector: A Comparative Analysis of Machine Learning Algorithms

Abstract

Customer segmentation is a critical strategy in the banking sector, enabling banks to tailor their products and services to meet the diverse needs of their customer base. This study explores the application of machine learning algorithms—K-Means Clustering, Hierarchical Clustering, and Gaussian Mixture Models (GMM)—for customer segmentation in the banking sector. The findings reveal that K-Means Clustering, with a silhouette score of 0.62, is highly effective for creating distinct and easily interpretable customer segments, making it suitable for scenarios requiring efficiency. Hierarchical Clustering offers deeper insights into customer relationships but is less efficient for large datasets. GMM provides the most flexible approach, capturing complex and overlapping customer behaviors, but requires significant computational resources and poses interpretability challenges. The results underscore the importance of selecting the appropriate algorithm based on segmentation objectives and resource constraints, ultimately enhancing targeted marketing and customer satisfaction in the banking sector.