TensorFlow Implementation of Neural Attentive Item Similarity Model for Recommendation on TKDE 2018
It includes the source codes of a deep knowledge-based recommendation KAC, and the datasets of Douban movie and NetEase music to evaluate the model
A pure Python implement of Collaborative Filtering based on MovieLens' dataset.
KGAT: Knowledge Graph Attention Network for Recommendation, KDD2019
Recommendation system based on knowledge graph embedding
The personalized recommendation system is an intelligent platform based on massive data mining. It can simulate store sales personnel to provide product information and suggestions to customers, and provide fully personalized decision support and information services for customers' shopping. Its goal is to Satisfying the needs of users, meeting the needs that users are not aware of, or realizing, but not expressing the needs, allowing users to go beyond the individual's vision and avoid seeing the trees without seeing the forest. A good recommendation system can greatly increase user loyalty and bring huge benefits to e-commerce. Personalized recommendation is to recommend information and products of interest to users according to their interests and purchasing behavior. As the scale of e-commerce continues to expand, the number and variety of products grow rapidly, and customers need to spend a lot of time to find the products they want to buy. This kind of browsing of a large amount of unrelated information and product processes will undoubtedly cause consumers who are drowning in information overload problems to continue to lose. In order to solve these problems, a personalized recommendation system came into being. The recommendation system is a branch of data mining. It is a special data mining system, which is mainly reflected in the real-time and interactivity of the recommendation system. The system recommends information that meets the interests of the user according to the user's interests, also known as the personalized recommendation system. It not only based on the user's past history, but also needs to react in real time with the behavior of the current period of time, and correct and optimize the recommendation result according to the feedback result of interaction with the user.
