<![CDATA[Customer segmentation is one of the key strategies that can help banks understand customer behavior and develop more effective service strategies. To achieve this goal, the K-Means Clustering method is used in this study to group ATM transaction data from Bank BJB Tasikmalaya Branch into four clusters with different characteristics. The analysis results show that Cluster 0 has 33 members, Cluster 1 consists of 94 members, Cluster 2 contains 136 members, and Cluster 3 includes 171 members. Each cluster shows significant differences in transaction frequency, with Cluster 3 having the largest number of members. Clustering evaluation and validation were carried out using the Elbow and Silhouette Score methods, which indicate high-quality segmentation. Visualization with PCA is used to help interpret the distribution and characteristics of each cluster. This research provides important insights for Bank BJB in developing more targeted marketing strategies, loyalty programs, and more personalized services according to the characteristics of each customer cluster. With the implementation of K-Means Clustering, Bank BJB can improve operational efficiency and customer satisfaction and strengthen its competitiveness in the digital era.]]>
Copyrights © 2025
