LRFS: Online shoppers behavior based efficient customer segmentation model

In the modern digital commerce environment, understanding customer behavior is pivotal for businesses to remain competitive and enhance customer retention.Traditional segmentation approaches often fail to capture the dynamic and multifaceted nature of online shoppers.This paper proposes the LRFS (Length, Recency, Frequency, and Spending) model, an extension of the RFM (Recency, Frequency, Monetary) model, specifically tailored for e-commerce platforms.By incorporating "Length"-the total span of a customer's activity-and integrating behavioral data such as page views, clicks, and dwell time, the LRFS model offers a more nuanced and dynamic segmentation of customers.Using clustering algorithms such as K-Means and Hierarchical Clustering, we analyze customer groups based on their online shopping behavior.The proposed system is tested on a real-world e-commerce dataset, and results demonstrate that LRFS-based segmentation outperforms traditional methods in identifying high-value, dormant, and at-risk customers.These insights are crucial for personalized marketing strategies and targeted customer engagement.