Businesses use customer segmentation as a strategic tool to divide their heterogeneous client base into discrete groups according to demands, behaviors, or common traits. An overview of consumer segmentation techniques is given in this paper, with emphasis on the role that this technique plays in promoting focused marketing campaigns, raising customer satisfaction levels, and allocating resources as efficiently as possible. This research investigates the effectiveness of real-time banking transaction data for customer segmentation using a large dataset 1048567 transaction. We explore various unsupervised machine learning algorithms to uncover hidden patterns and group customers with similar financial behavior. The methods employed include K-means clustering with standard scaling for normalization, hierarchical clustering with an agglomerative approach for building a hierarchy of clusters, DBSCAN (Density-Based Spatial Clustering of Applications with Noise) for identifying clusters of arbitrary shapes, and Principal Component Analysis (PCA) for dimensionality reduction to focus on the most significant features within the data. By applying these diverse algorithms, we aim to achieve a comprehensive understanding of customer segmentation based on real-time transaction patterns. The analysis will reveal distinct customer groups based on factors such as frequency, type, and value of transactions, allowing banks to develop targeted strategies for improved customer satisfaction and retention.