## Learning Attribute-to-Feature Mappings for Cold-Start Recommendations

No Thumbnail Available
##### Files
There are no files associated with this item.
2010
##### Authors
Gantner, Zeno
Drumond, Lucas
Schmidt-Thieme, Lars
##### Publication type
Contribution to a conference collection
##### Published in
2010 IEEE International Conference on Data Mining. - IEEE, 2010. - pp. 176-185. - ISBN 978-1-4244-9131-5
##### Abstract
Cold-start scenarios in recommender systems are situations in which no prior events, like ratings or clicks, are known for certain users or items. To compute predictions in such cases, additional information about users (user attributes, e.g. gender, age, geographical location, occupation) and items (item attributes, e.g. genres, product categories, keywords) must be used. We describe a method that maps such entity (e.g. user or item) attributes to the latent features of a matrix (or higher-dimensional) factorization model. With such mappings, the factors of a MF model trained by standard techniques can be applied to the new-user and the new-item problem, while retaining its advantages, in particular speed and predictive accuracy. We use the mapping concept to construct an attribute-aware matrix factorization model for item recommendation from implicit, positive-only feedback. Experiments on the new-item problem show that this approach provides good predictive accuracy, while the prediction time only grows by a constant factor.
##### Subject (DDC)
004 Computer Science
##### Keywords
collaborative filtering,cold-start,matrix factorization,factorization models,long tail,recommender systems
##### Conference
2010 IEEE 10th International Conference on Data Mining (ICDM), Dec 13, 2010 - Dec 17, 2010, Sydney, Australia
##### Cite This
ISO 690GANTNER, Zeno, Lucas DRUMOND, Christoph FREUDENTHALER, Steffen RENDLE, Lars SCHMIDT-THIEME, 2010. Learning Attribute-to-Feature Mappings for Cold-Start Recommendations. 2010 IEEE 10th International Conference on Data Mining (ICDM). Sydney, Australia, Dec 13, 2010 - Dec 17, 2010. In: 2010 IEEE International Conference on Data Mining. IEEE, pp. 176-185. ISBN 978-1-4244-9131-5. Available under: doi: 10.1109/ICDM.2010.129
BibTex
@inproceedings{Gantner2010-12Learn-12687,
year={2010},
doi={10.1109/ICDM.2010.129},
title={Learning Attribute-to-Feature Mappings for Cold-Start Recommendations},
isbn={978-1-4244-9131-5},
publisher={IEEE},
booktitle={2010 IEEE International Conference on Data Mining},
pages={176--185},
author={Gantner, Zeno and Drumond, Lucas and Freudenthaler, Christoph and Rendle, Steffen and Schmidt-Thieme, Lars}
}

RDF
<rdf:RDF
xmlns:dcterms="http://purl.org/dc/terms/"
xmlns:dc="http://purl.org/dc/elements/1.1/"
xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
xmlns:bibo="http://purl.org/ontology/bibo/"
xmlns:dspace="http://digital-repositories.org/ontologies/dspace/0.1.0#"
xmlns:foaf="http://xmlns.com/foaf/0.1/"
xmlns:void="http://rdfs.org/ns/void#"
xmlns:xsd="http://www.w3.org/2001/XMLSchema#" >
<foaf:homepage rdf:resource="http://localhost:8080/"/>
<dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2011-09-08T06:24:31Z</dc:date>
<bibo:uri rdf:resource="http://kops.uni-konstanz.de/handle/123456789/12687"/>
<dc:rights>terms-of-use</dc:rights>
<dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
<dcterms:issued>2010-12</dcterms:issued>
<dcterms:bibliographicCitation>First publ. in: 2010 IEEE 10th International Conference on Data Mining (ICDM 2010) : Sydney, Australia, 13 - 17 December 2010 ; [proceedings] / [IEEE Computer Society]. Ed.: Geoffrey I. Webb ... . Piscataway, NJ : IEEE, 2010, pp. 176-185</dcterms:bibliographicCitation>
<dc:creator>Drumond, Lucas</dc:creator>
<dcterms:abstract xml:lang="eng">Cold-start scenarios in recommender systems are situations in which no prior events, like ratings or clicks, are known for certain users or items. To compute predictions in such cases, additional information about users (user attributes, e.g. gender, age, geographical location, occupation) and items (item attributes, e.g. genres, product categories, keywords) must be used. We describe a method that maps such entity (e.g. user or item) attributes to the latent features of a matrix (or higher-dimensional) factorization model. With such mappings, the factors of a MF model trained by standard techniques can be applied to the new-user and the new-item problem, while retaining its advantages, in particular speed and predictive accuracy. We use the mapping concept to construct an attribute-aware matrix factorization model for item recommendation from implicit, positive-only feedback. Experiments on the new-item problem show that this approach provides good predictive accuracy, while the prediction time only grows by a constant factor.</dcterms:abstract>
<dc:language>eng</dc:language>
<dc:contributor>Drumond, Lucas</dc:contributor>
<dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2011-09-08T06:24:31Z</dcterms:available>
<dc:creator>Gantner, Zeno</dc:creator>
<dcterms:title>Learning Attribute-to-Feature Mappings for Cold-Start Recommendations</dcterms:title>
<dc:contributor>Freudenthaler, Christoph</dc:contributor>
<void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/>
<dc:contributor>Rendle, Steffen</dc:contributor>
<dc:contributor>Schmidt-Thieme, Lars</dc:contributor>
<dcterms:rights rdf:resource="https://rightsstatements.org/page/InC/1.0/"/>
<dc:creator>Rendle, Steffen</dc:creator>
<dc:creator>Freudenthaler, Christoph</dc:creator>
<dc:creator>Schmidt-Thieme, Lars</dc:creator>
<dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
<dc:contributor>Gantner, Zeno</dc:contributor>
</rdf:Description>
</rdf:RDF>

No