In recent years, with the rapid development of mobile Internet, more and more industries have begun to adopt mobile Internet technology, provide diversified wireless services, and further expand user activity scenarios. The core of reducing customer loss is to identify potential customers. In order to solve the problem of how to accurately predict the loss of customers, this paper put forward an invented method to verify and compared the model with the customer data of an e-commerce enterprise in China. According to the research results, the improved XGBoost algorithm can effectively reduce the probability of class I errors and has higher accuracy, among which the accuracy has increased by 2.8%. The prediction effect of customer groups after segmentation was better than that before segmentation, in which the probability of the occurrence of class I errors in the prediction of core value customers decreases by 10.8% and the accuracy rate increases by 7.8%. Compared with other classification algorithms, the improved XGBoost algorithm had a significant improvement in AUC value accuracy rate and other indicators. This fully shows that the XGBoost algorithm can effectively predict the loss of e-commerce customers and then provide decision-making reference for the customer service strategy of e-commerce enterprises.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.