Kabbur等［9］提出了进一步表达用户信息的因子项目相似性模型factored itemsimilarity modelsFISM。此模型本质上是基于物品的协同推荐算法它将用户历史评分过的物品作为特征属性来得到用户表示用户表示与物品表示的内积来表达用户对物品的偏好。SVD++模型［10］则结合了基于用户的推荐算法和基于物品的推荐算法这两者的优势。重写一下上面这段话

Kabbur et al. proposed a model called Factored Item Similarity Models (FISM) that aims to express user information through the similarity of item features. FISM is essentially a collaborative filtering algorithm that uses the items that a user has rated in the past as feature attributes to obtain a user representation. The user's preference for an item is expressed by the dot product of the user representation and the item representation. Additionally, the SVD++ model combines the strengths of both user-based and item-based recommendation algorithms.