Comparing product specifications to solve the cold start problem in a recommender system

Aciar, S; Aciar, G; Zhang, D

Comparing product specifications to solve the cold start problem in a recommender system

Aciar, S Aciar, G Zhang, D

Permalink

Publication Type:: Conference Proceeding
Citation:: Proceedings of the 2016 42nd Latin American Computing Conference, CLEI 2016, 2017
Issue Date:: 2017-01-25

Closed Access

	Filename	Description	Size
	07833354.pdf	Published version	386.15 kB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Aciar, S	en_US
dc.contributor.author	Aciar, G	en_US
dc.contributor.author	Zhang, D	en_US
dc.date.issued	2017-01-25	en_US
dc.identifier.citation	Proceedings of the 2016 42nd Latin American Computing Conference, CLEI 2016, 2017	en_US
dc.identifier.isbn	9781509016334	en_US
dc.identifier.uri	http://hdl.handle.net/10453/125996
dc.description.abstract	© 2016 IEEE. Recommender systems are widely used applications to solve the problems of information overload, usually on websites. A well-known problem of recommender systems is the problem of cold start, which is caused by the lack of data. A recommendation system can only produce good recommendations after it has accumulated enough data The problem becomes even more challenging when the recommender system comes to deal with new products or the products have not been evaluated by consumers. This paper addresses this problem based on a comparison of product specifications, experiments were conducted in the recommendation domain of digital cameras.	en_US
dc.relation.ispartof	Proceedings of the 2016 42nd Latin American Computing Conference, CLEI 2016	en_US
dc.relation.isbasedon	10.1109/CLEI.2016.7833354	en_US
dc.title	Comparing product specifications to solve the cold start problem in a recommender system	en_US
dc.type	Conference Proceeding
utslib.for	0806 Information Systems	en_US
pubs.embargo.period	Not known	en_US
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/School of Systems, Management and Leadership
utslib.copyright.status	closed_access
pubs.publication-status	Published	en_US

Abstract:

© 2016 IEEE. Recommender systems are widely used applications to solve the problems of information overload, usually on websites. A well-known problem of recommender systems is the problem of cold start, which is caused by the lack of data. A recommendation system can only produce good recommendations after it has accumulated enough data The problem becomes even more challenging when the recommender system comes to deal with new products or the products have not been evaluated by consumers. This paper addresses this problem based on a comparison of product specifications, experiments were conducted in the recommendation domain of digital cameras.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/125996