A new model of selecting most relevant ratings in recommender systems

摘要

A major assumption of collaborative filtering is that similar users will always agree on a majority of items, regardless of their domain. This concept establishes strong connections among neighbors. However, it eliminates potentially good users on the premise that they are not similar enough. Furthermore, this assumption allows for the possibility of a neighbor to be chosen simply because he/she shares a lot of similar ratings in unrelated domains and offers little useful information in the active item domain. This effectively reduces the amount of useful information that is considered for each recommendation. We propose a new way to identify relevant ratings that relies on somewhat weaker, but more abundantly available neighbors.