Predicting neighbor goodness in collaborative filtering
Entity
UAM. Departamento de Ingeniería InformáticaPublisher
Springer Berlin HeidelbergDate
2009Citation
10.1007/978-3-642-04957-6_52
Flexible Query Answering Systems: 8th International Conference, FQAS 2009, Roskilde, Denmark, October 26-28, 2009. Proceedings. Lecture Notes in Computer Science, Volumen 5822. Springer, 2009. 605-616.
ISSN
0302-9743 (print); 1611-3349 (online)ISBN
978-3-642-04956-9 (print); 978-3-642-04957-6 (online)DOI
10.1007/978-3-642-04957-6_52Funded by
This work was supported by the Spanish Ministry of Science and Innovation (TIN2008-06566-C04-02) and the Ministry of Industry, Tourism and Commerce (CENIT-2007-1012).Editor's Version
http://dx.doi.org/10.1007/978-3-642-04957-6_52Subjects
Collaborative filtering; Neighbor selection; Performance prediction; Query clarity; Recommender systems; InformáticaNote
Proceedings of 8th International Conference, FQAS 2009, Roskilde, Denmark, October 26-28, 2009.The final publication is available at Springer via http://dx.doi.org/10.1007/978-3-642-04957-6_52
Rights
© Springer-Verlag Berlin Heidelberg 2009Abstract
Performance prediction has gained increasing attention in the IR field since the half of the past decade and has become an established research topic in the field. The present work restates the problem in the subarea of Collaborative Filtering (CF), where it has barely been researched so far. We investigate the adaptation of clarity-based query performance predictors to define predictors of neighbor performance in CF. The proposed predictors are introduced in a memory-based CF algorithm to produce a dynamic variant where neighbor ratings are weighted based on their predicted performance. The approach is tested with encouraging empirical results, as the dynamic variants consistently outperform the baseline algorithms, with increasing difference on small neighborhoods.
Files in this item
Google Scholar:Bellogin Kouki, Alejandro
-
Castells Azpilicueta, Pablo
This item appears in the following Collection(s)
Related items
Showing items related by title, author, creator and subject.