Personalized Recommendation Model for Mobile E-commerce Users

Aiming at the technical problems of data sparsity and real-time recommendation in mobile e-commerce, this paper proposes a personalized recommendation algorithm based on user purchase preference and the interest of traditional user collaborative filtering recommendation. In online recommendation, the user's real-time behavior characteristics are brought into the behavior model to get the user's purchase tendency. Then combined with the interest degree, the product with the highest purchase probability is recommended to the user. We use the relevant algorithms to mine the information in the mobile e-commerce transaction database to achieve the unity of real-time and accuracy. Finally, the proposed classification model is verified on a real data set. The experimental results show that the proposed method can provide personalized real-time recommendation for mobile users better than other traditional methods to improve the consumer satisfaction.