Research on Anime Recommendation Algorithm Based on Parallel Feature Interaction

In recent years, the animation industry has experienced rapid growth, leading to an explosive increase in available animation resources. How to accurately recommend personalized animation content for users has emerged as a significant challenge in the industry. Due to the diversity of user preferences and animation content characteristics, the application of recommender systems in the field of animation faces great challenges. In order to solve the problem that it is difficult for users to find content that meets their interests in massive resources, the research of personalized recommendation algorithm is of great significance. Building on an analysis of current recommendation models, this paper presents a personalized anime recommendation algorithm based on parallel feature interaction. The algorithm combines multi-dimensional features such as user viewing history, interest preference, style and theme of animation content, and deeply excavates the relationship between users and animation resources through parallel feature interaction modeling, and finally realizes personalized recommendation. Experimental results demonstrate that the proposed algorithm performs exceptionally well in recommendation accuracy and has important application value for content distribution and user experience improvement in the animation industry.