A Collaborative Filtering Algorithm Combined with User Habits for Rating
Min Li, Kai Zheng · Advances in intelligent systems research/Advances in Intelligent Systems Research · 2015
Collaborative filtering is one of the most successful and widely used technologies in personalized recommendation systems.This paper proposed a novel algorithm combined with user habits for rating as the conventional method leads lower accuracy relatively.In order to reveal the hidden relationship between users, the new algorithm not only reserves the traditional measure but also takes Bhattacharyya Coefficient and entropy into account while calculating the user similarities.Experiment results show the new algorithm outperforms the conventional method.