Title :
User and Item Pattern Matching in Multi-criteria Recommender Systems
Author :
Poompuang, Pitaya ; Premchaiswadi, Wichian
Author_Institution :
Grad. Sch. of IT in Bus., Siam Univ., Bangkok, Thailand
Abstract :
Information on the ratings of several features of items can be deployed to improve the quality of recommendations in recommender systems by incorporating them into similarity calculation between any two users or two items. However, the incremental information of these features has important impacts on recommender systems. For example, the complexity of similarity calculation is increased and more resources are consumed during the process for generating recommendations. In this paper, we propose several techniques by using this information to provide relevant recommendations and to reduce the complexity in similarity computation by directly matching between preferences of user and the strength of item features.
Keywords :
computational complexity; pattern matching; recommender systems; item pattern matching; multicriteria recommender systems; similarity calculation complexity; Artificial intelligence; Distributed computing; Information filtering; Information filters; Motion pictures; Multidimensional systems; Pattern matching; Recommender systems; Software engineering; Software standards; item profile; multi-criteria; pattern matching; recommendation; recommender system; reduction; transformation; user profile;
Conference_Titel :
Software Engineering Artificial Intelligence Networking and Parallel/Distributed Computing (SNPD), 2010 11th ACIS International Conference on
Conference_Location :
London
Print_ISBN :
978-1-4244-7422-6
Electronic_ISBN :
978-1-4244-7421-9
DOI :
10.1109/SNPD.2010.13