Journal of Computational Methods in Sciences and Engineering, Journal Year: 2025, Volume and Issue: unknown

Published: April 28, 2025

This research addresses the critical challenge of customer churn prediction in cross-border e-commerce by proposing an enhanced XGBoost-based framework that integrates temporal-spatial features and dynamic weight adjustment mechanisms. In response to complex characteristics international e-commerce, including regional behavioral variations, seasonal patterns, logistics impacts, this study develops novel approaches feature engineering algorithm optimization. The model incorporates continuous temporal processing, adaptive adjustment, business rule-based interactions achieve superior performance. Through extensive experimentation with large-scale transaction datasets, demonstrates significant improvements accuracy across diverse geographical regions while maintaining interpretability. findings contribute substantially both theoretical advancement machine learning applications practical implementations relationship management. proposed provides valuable insights for platforms seeking implement more effective retention strategies optimize their operational efficiency global markets.

Language: Английский