SOM Neural Network for Bank Customer Segmentation

This analysis addresses the problem of unsupervised bank customer segmentation using a Self-Organizing Map (SOM), also known as a Kohonen map, applied to the high-dimensional Bank Marketing dataset. The main objective was to project 29 customer features (derived from 12 original variables like age, balance, and marital status) onto a 10x10 grid to reveal natural clusters and inform strategic marketing decisions. The SOM model successfully converged, reducing the quantification error by 29.12% over 200 epochs. The study identified five distinct customer profiles, including: young, highly educated singles; married clients with high financial burden (mortgages/loans); and, most strategically, a segment of clients with a historically successful prior campaign contact (Perfil D). The segregation of these profiles validates the SOM’s ability to transform the complex, 29-dimension space into an interpretable 2D map, providing a solid foundation for prioritizing resources toward the most receptive segments.