An Evaluation Methodology for Collaborative Recommender Systems
Authors:
- Paolo CremonesiPCPaolo Cremonesi
- Roberto TurrinRTRoberto Turrin
- Eugenio LentiniELEugenio Lentini
- Matteo MatteucciMMMatteo Matteucci
- 1 November 2008
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 224-231
Abstract
Recommender systems use statistical and knowledge discovery techniques in order to recommend products to users and to mitigate the problem of information overload. The evaluation of the quality of recommender systems has become an important issue for choosing the best learning algorithms. In this paper we propose an evaluation methodology for collaborative filtering (CF) algorithms. This methodology carries out a clear, guided and repeatable evaluation of a CF algorithm. We apply the methodology on two datasets, with different characteristics, using two CF algorithms: singular value decomposition and naive bayesian networks.Keywords
This publication has 9 references indexed in Scilit:
- Qualitative analysis of user-based and item-based prediction algorithms for recommendation agentsEngineering Applications of Artificial Intelligence, 2005
- Item-based top-Nrecommendation algorithmsACM Transactions on Information Systems, 2004
- Evaluating collaborative filtering recommender systemsACM Transactions on Information Systems, 2004
- Item-based collaborative filtering recommendation algorithms2001
- Analysis of recommendation algorithms for e-commerce2000
- An algorithmic framework for performing collaborative filtering1999
- GroupLensCommunications of the ACM, 1997
- Using Linear Algebra for Intelligent Information RetrievalSIAM Review, 1995
- Social information filtering1995