Title :
A Research on Fuzzy Formal Concept Analysis Based Collaborative Filtering Recommendation System
Author :
Fang, Peici ; Zheng, Siyao
Author_Institution :
Sch. of Comput. Sci. & Eng., BeiHang Univ., Beijing, China
fDate :
Nov. 30 2009-Dec. 1 2009
Abstract :
A novel method for collaborative filtering recommendation based on fuzzy formal concept analysis is proposed in this paper, including the algorithm for user rating matrix fuzzification, the algorithm generating fuzzy concept for rating prediction and the algorithm generating predicting rating. Fuzzy formal concept analysis is a means of conceptual clustering, it not only solves the high sparsity problem of user rating matrix, but also be more efficient when the matrix is more sparse. Sharp edge problem is also solved because of the introduction of fuzzy logic. The experiment applied on a common used Movielens database shows the reasonable accuracy and time efficiency of the proposed collaborative filtering recommendation system.
Keywords :
fuzzy set theory; matrix algebra; recommender systems; collaborative filtering recommendation system; fuzzy formal concept analysis; fuzzy logic; sharp edge problem; sparsity problem; user rating matrix fuzzification; Algorithm design and analysis; Clustering algorithms; Collaboration; Filtering algorithms; Fuzzy logic; Fuzzy sets; Fuzzy systems; History; Motion pictures; Sparse matrices; collaborative filtering recommendation; formal concept analysis; fuzzy concept analysis; fuzzy logic;
Conference_Titel :
Knowledge Acquisition and Modeling, 2009. KAM '09. Second International Symposium on
Conference_Location :
Wuhan
Print_ISBN :
978-0-7695-3888-4
DOI :
10.1109/KAM.2009.40