In the competitive realm of e-commerce, the strategic use of customer data stands as a cornerstone for achieving success. The advent of the COVID-19 pandemic has notably shifted consumer shopping preferences toward online platforms, spotlighting the critical role of customer segmentation in adapting to these changes. This study delves into the advanced utilization of consumer purchase behavior analytics within e-commerce environments to achieve sophisticated customer segmentation. It introduces clustering, a pivotal machine learning technique, as a means for computers to efficiently parse and understand complex datasets. By integrating the recency, frequency, monetary (RFM) model with the k-means clustering algorithm, the research demonstrates a methodical approach to segregating customers into meaningful groups. This process not only aids in identifying the most lucrative customer segments but also in tailoring strategic marketing plans to each, thereby amplifying profitability through targeted engagement. The evaluation of cluster quality, based on e-commerce transaction data, further enriches the study by validating the effectiveness of these segmentation strategies.