By comparing similar items rather than similar customers, item-to-item collaborative filtering scales to very large data sets and produces high-quality recommendations.
internet, 7(1):76-80, 2003. [doi]The increasing users and items restrict the development of collaborative filtering recommendation systems. Then a series of problems, such as sparsity, cold ..., and it can be more veracious and better recommendation quality. The experiment
wkdd 2009: 60-63 [doi]