B2C E-Commerce Customer Churn Prediction Based on K-Means and SVM

Customer churn prediction is very important for e-commerce enterprises to formulate effective customer retention measures and implement successful marketing strategies. According the characteristics of longitudinal timelines multidimensional data variables B2C customers’ shopping behaviors, this paper proposes a loss model based on combination k-means segmentation support vector machine (SVM) prediction. The method divides customers into three categories determines core groups. logistic regression were compared predict churn. results show that each index after was significantly improved, which proves clustering necessary. accuracy SVM higher than These research have significance relationship management enterprises.