As the heterogeneity of data sources are increasing on the web, and due to the sparsity of data in each of these data sources, cross-domain recommendation is becoming an emerging research topic in the recent years. Cross-domain collaborative filtering aims to transfer the user rating pattern from source (auxiliary) domains to a target domain for the purpose of alleviating the sparsity problem and providing better target recommendations. However, the studies so far have either focused on a limited number of domains that are assumed to be related to each other (such as books and movies), or a division of the same dataset (such as movies) into different domains based on an item characteristic (such as genre). In this paper, we study a broad set of domains and their characteristics to understand the factors that affect the success or failure of cross-domain collaborative filtering, the amount of improvement in cross-domain approaches, and the selection of best source domains for a specific target domain. We propose to use Canonical Correlation Analysis (CCA) as a significant major factor in finding the most promising source domains for a target domain, and suggest a cross-domain collaborative filtering based on CCA (CD-CCA) that proves to be successful in using the shared information between domains in the target recommendations.
%0 Conference Paper
%1 citeulike:13986080
%A Sahebi, Shaghayegh
%A Brusilovsky, Peter
%B Proceedings of the 9th ACM Conference on Recommender Systems
%C New York, NY, USA
%D 2015
%I ACM
%K cross-domain recommender
%P 131--138
%R 10.1145/2792838.2800188
%T It Takes Two to Tango: An Exploration of Domain Pairs for Cross-Domain Collaborative Filtering
%U http://dx.doi.org/10.1145/2792838.2800188
%X As the heterogeneity of data sources are increasing on the web, and due to the sparsity of data in each of these data sources, cross-domain recommendation is becoming an emerging research topic in the recent years. Cross-domain collaborative filtering aims to transfer the user rating pattern from source (auxiliary) domains to a target domain for the purpose of alleviating the sparsity problem and providing better target recommendations. However, the studies so far have either focused on a limited number of domains that are assumed to be related to each other (such as books and movies), or a division of the same dataset (such as movies) into different domains based on an item characteristic (such as genre). In this paper, we study a broad set of domains and their characteristics to understand the factors that affect the success or failure of cross-domain collaborative filtering, the amount of improvement in cross-domain approaches, and the selection of best source domains for a specific target domain. We propose to use Canonical Correlation Analysis (CCA) as a significant major factor in finding the most promising source domains for a target domain, and suggest a cross-domain collaborative filtering based on CCA (CD-CCA) that proves to be successful in using the shared information between domains in the target recommendations.
%@ 978-1-4503-3692-5
@inproceedings{citeulike:13986080,
abstract = {{As the heterogeneity of data sources are increasing on the web, and due to the sparsity of data in each of these data sources, cross-domain recommendation is becoming an emerging research topic in the recent years. Cross-domain collaborative filtering aims to transfer the user rating pattern from source (auxiliary) domains to a target domain for the purpose of alleviating the sparsity problem and providing better target recommendations. However, the studies so far have either focused on a limited number of domains that are assumed to be related to each other (such as books and movies), or a division of the same dataset (such as movies) into different domains based on an item characteristic (such as genre). In this paper, we study a broad set of domains and their characteristics to understand the factors that affect the success or failure of cross-domain collaborative filtering, the amount of improvement in cross-domain approaches, and the selection of best source domains for a specific target domain. We propose to use Canonical Correlation Analysis (CCA) as a significant major factor in finding the most promising source domains for a target domain, and suggest a cross-domain collaborative filtering based on CCA (CD-CCA) that proves to be successful in using the shared information between domains in the target recommendations.}},
added-at = {2018-03-19T12:24:51.000+0100},
address = {New York, NY, USA},
author = {Sahebi, Shaghayegh and Brusilovsky, Peter},
biburl = {https://www.bibsonomy.org/bibtex/2d11baf64e2f55ec57d037dfcb6c86bb0/aho},
booktitle = {Proceedings of the 9th ACM Conference on Recommender Systems},
citeulike-article-id = {13986080},
citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=2792838.2800188},
citeulike-linkout-1 = {http://dx.doi.org/10.1145/2792838.2800188},
doi = {10.1145/2792838.2800188},
interhash = {9d5b5cf77dd14b07c6062ece1e1b4ae9},
intrahash = {d11baf64e2f55ec57d037dfcb6c86bb0},
isbn = {978-1-4503-3692-5},
keywords = {cross-domain recommender},
location = {Vienna, Austria},
pages = {131--138},
posted-at = {2016-03-23 01:39:16},
priority = {2},
publisher = {ACM},
series = {RecSys '15},
timestamp = {2018-03-19T12:24:51.000+0100},
title = {{It Takes Two to Tango: An Exploration of Domain Pairs for Cross-Domain Collaborative Filtering}},
url = {http://dx.doi.org/10.1145/2792838.2800188},
year = 2015
}