Data analytics is essential in the e-commerce sector since it improves customer relationship management (CRM) techniques and offers businesses valuable insights to customize client interactions. However, conventional RFM analysis often fails to capture rapidly changing customer behaviors, which lack the agility needed in today’s fast-paced market. This discrepancy underscores the necessity for a more dynamic approach that can accurately reflect and adapt to the evolving patterns of consumer activity, ensuring that CRM strategies remain effective and relevant over time. Our study addressed the identified gap by proposing a sophisticated time-weighted RFM model, enhanced with K-means++ clustering, for real-time customer behavior analysis. Improving customer segmentation in e-commerce captures a robust and more dynamic profile for consumer behaviors. Allowing businesses to implement real-time preemptive commerce strategies and back-office navigation routes using an advanced understanding of customer engagement patterns in digital commerce ultimately creates a new standard for CRM performance today. Increased segmentation accuracy reveals the effectiveness of our model, where silhouette scores improve up to 0.45, meaning that more compact and separate clusters are generated now. Further, campaign response rates improved by 15% due to better customer engagement with the model. These same customer retention metrics indicate a corresponding rise in engagement, demonstrating the model’s real-world impact on business growth and client loyalty. The results show that our method improves CRM strategies in the e-commerce field.