Recommendation Technologies: Survey of Current Methods and Possible Extensions
39 Pages Posted: 9 Oct 2008
Date Written: 2004
The paper presents a survey of the field of recommender systems anddescribes current recommendation methods that are usually classified into thefollowing three main categories: content-based, collaborative, and hybridrecommendation approaches. The paper also describes various limitations ofcurrent recommendation methods and discusses possible extensions that canimprove recommendation capabilities. These extensions include, among others,improvement of understanding of users and items, incorporation of the contextualinformation into the recommendation process, support for multi-criteria ratings,and provision of more flexible and less intrusive types of recommendations.
Keywords: recommender systems, survey, rating estimation methods, extensions to recommender systems
Suggested Citation: Suggested Citation