 Research on E-Commerce Return Prediction and Influencing Factor Analysis Based on User Behavioral CharacteristicsMe Sun Pinnacle Academic Press Proceedings Series, 2025, vol. 3, 15-28 Abstract: This research presents a comprehensive investigation into e-commerce return prediction utilizing user behavioral characteristics and machine learning methodologies. The study develops a predictive framework that analyzes consumer interaction patterns, purchase history, and demographic factors to forecast return likelihood across different product categories. Through extensive experimentation on real-world e-commerce datasets, multiple machine learning algorithms are evaluated including random forest, gradient boosting, and neural networks. The research identifies key behavioral indicators such as browsing duration, product comparison frequency, and historical return rates as primary predictors. Results demonstrate that the proposed approach achieves 89.3% accuracy in return prediction while reducing false positive rates by 23% compared to baseline methods. The findings reveal significant temporal patterns in return behavior and establish quantitative relationships between user characteristics and return probability. This work contributes to the optimization of inventory management and customer satisfaction in e-commerce platforms. Keywords: e-commerce returns; user behavior analysis; predictive modeling; machine learning (search for similar items in EconPapers) Downloads: (external link) Related works: Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text Persistent link: https://EconPapers.repec.org/RePEc:dba:pappsa:v:3:y:2025:i::p:15-28 Access Statistics for this article More articles in Pinnacle Academic Press Proceedings Series from Pinnacle Academic Press |
Is your work missing from RePEc? Here is how to contribute.
Questions or problems? Check the EconPapers FAQ or send mail to .
EconPapers is hosted by the
School of Business at Örebro University.