Intelligent Recommendation Method for Product Information of E-commerce Platform Based on Machine Learning Algorithm

Product recommendation has become an important way to alleviate the overload of e-commerce shopping information. In order to provide personalized recommendations, the recommendation system will express users and items as user preference vectors and item feature vectors, respectively. Different dimensions in the item feature vector correspond to different features of the item. Each dimension in the user preference vector represents the user's preference for the corresponding dimension of the item. Currently, most recommendation algorithms assume that the preference vectors for different items and the same user are the same. However, in real life, this assumption is not tenable. Therefore, this article proposes a DARR model to solve the above problems, and compares it on the public recommendation dataset to verify the effectiveness of the model.