Keywords
XGBoost Model
After-sales issues
Prediction
Submitted : 2024-11-23
Accepted : 2024-12-08
Published : 2024-12-23
Abstract
This study investigates the application of machine learning models to address after-sales service issues in cross-border e-commerce, focusing on predicting order returns to reduce return costs and optimize customer experience. Using H cross-border e-commerce company as a case study, the research employs Random Forest and XGBoost models to identify high-risk return orders. By comparing the performance of these two models, the study highlights their respective strengths and weaknesses and proposes optimization strategies. The findings provide a valuable reference for e-commerce companies to refine their business models, reduce return rates, improve operational efficiency, and enhance customer satisfaction.
References
Statista, 2024, Cross-Border E-Commerce.
Chen S, 2023, Study on Customer Satisfaction of Cross-Border Import E-Commerce Logistics Service Based on Online Review, dissertation, Tongji University.
Xie W, 2024, Prediction of Cross-Border E-Commerce Sales Volume Based on Machine Learning, dissertation, Jilin University.
Qian Y, 2023, Research on User Behavior for E-commerce Platforms Based on Machine Learning, dissertation, Tianjin University of Commerce.
Shi Y, 2021, Research on E-Commerce Customer Value Identification Based on Improved RFM Model, dissertation, Harbin University of Commerce.
Yang S, 2023, 2023, Study on Customer Satisfaction of Cross-Border Import E-Commerce Logistics Service Based on Online Review, dissertation, Donghua University.
Zhao M, Wang Z, 2020, Prediction of Customer Returns in E-Commerce Based on Random Forest. Journal of Retailing and Consumer Services, 55: 102070.
Song J, 2023, Prediction and Analysis of B2C User Purchase Behavior Based on Machine Learning, dissertation, Northeast Normal University.
Li M, 2023, E-Commerce User Purchase Behavior Prediction Based on Machine Learning Methods, dissertation, Dongbei University of Finance and Economics.
Liu Y, 2023, E-Commerce Customer Loss Prediction Based on Machine Learning, dissertation, Southwest University.
Li T, 2022, Research on the Improvement of Customer Satisfaction of Home Appliances Based on E-Commerce Data Mining, dissertation, Capital University of Economics and Business.
Shi W, Liu X, Wang J, 2021, Addressing Class Imbalance in E-Commerce Returns Prediction Using Resampling Techniques and XGBoost. Journal of Business Research, 127: 145–153.
Zhou Y, Chen F, Li Q, 2022, Enhancing E-Commerce Prediction Models Through XGBoost and User Behavior Analytics. Journal of E-Commerce Research, 9(3): 202–215.
Yang Y, Zou X, Li C, 2023, User Purchase Behavior Prediction Method Based on XGBoost. Electronics, 12(9).
Chen T, Guestrin C, 2016, XGBoost: A Scalable Tree Boosting System. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 785–794. https://doi.org/10.1145/2939672.2939785