Improved Slope One Algorithm Based On Time Weight

摘要

Collaborative filtering is regarded as the most prevailing techniques for recommendation system. Slope one is a family of algorithms used for collaborative filtering. It is the simplest form of non-trivial item-based collaborative filtering based on ratings. But all the family of use CF algorithms ignores one important problem: ratings produced at different times are weighted equally. It means that they can't catch user's different attitudes at different time. So in this paper, we present a new algorithm, which could assign different weights for items at different time. Finally, we experimentally evaluate our approach and compare it to the original Slope One. The experiment shows that the new slope one algorithms can improve the precision.