Preference networks : probabilistic models for recommendation systems
Contribuinte(s) |
Christen, Peter Kennedy, Paul Li, Jiuyong Kolyshkina, Inna Williams, Graham |
---|---|
Data(s) |
01/01/2007
|
Resumo |
Recommender systems are important to help users select relevant and personalised information over massive amounts of data available. We propose an unified framework called Preference Network (PN) that jointly models various types of domain knowledge for the task of recommendation. The PN is a probabilistic model that systematically combines both content-based filtering and collaborative filtering into a single conditional Markov random field. Once estimated, it serves as a probabilistic database that supports various useful queries such as rating prediction and top-N recommendation. To handle the challenging problem of learning large networks of users and items, we employ a simple but effective pseudo-likelihood with regularisation. Experiments on the movie rating data demonstrate the merits of the PN.<br /> |
Identificador | |
Idioma(s) |
eng |
Publicador |
Australian Computer Society |
Relação |
http://dro.deakin.edu.au/eserv/DU:30044800/phung-preferencenetworks-2007.pdf http://crpit.com/confpapers/CRPITV70Truyen.pdf |
Direitos |
2007, Australian Computer Society |
Palavras-Chave | #hybrid recommender systems #collaborative filtering #preference networks #conditional Markov networks #movie rating |
Tipo |
Conference Paper |