Cross-Border E-commerce User Feature Mining and Personalized Push Algorithm Based on User Behavioral Trajectory

The rapid development of the Internet has made cross-border e-commerce an important part of international trade. However, how to effectively mine the characteristics of cross-border e-commerce users and realize accurate push is still a major challenge for the industry. This paper proposes a cross-border e-commerce user feature mining and personalized push algorithm based on user behavioral trajectory, aiming to improve user experience and shopping conversion rate. This study constructs user behavior trajectories by collecting user behavior data on cross-border e-commerce platforms. Then, data mining and machine learning techniques are applied to deeply analyze the user behavior trajectory and extract key features such as users’ interest preferences and consumption habits. A personalized push algorithm is designed in this study. The algorithm recommends goods and services for users that are highly matched to their interests and needs based on their characteristics and behavioral patterns. By continuously optimizing the algorithm model, it achieves a balance between the accuracy and diversity of the push content and improves user satisfaction and loyalty. The cross-border e-commerce user feature mining and personalized push algorithm based on user behavioral trajectory proposed in this paper has achieved significant results in improving user experience and shopping conversion rate, which can better meet users’ needs and expectations and enhance users’ trust and reliance on cross-border e-commerce platforms. This study not only provides new ideas and methods for personalized push on cross-border e-commerce platforms, but also provides useful reference for user feature mining and precision marketing in other fields.