Information overload on the Web has created enormous challenges to customers selecting products for online purchases and to online businesses attempting to identify customers' preferences efficiently. Various recommender systems employing different data representations and recommendation methods are currently used to address these challenges. In this research, we developed a graph model that provides a generic data representation and can support different recommendation methods. To demonstrate its usefulness and flexibility, we developed three recommendation methods: direct retrieval, association mining, and high-degree association retrieval. We used a data set from an online bookstore as our research test-bed. Evaluation results showed that combining product content information and historical customer transaction information achieved more accurate predictions and relevant recommendations than using only collaborative information. However, comparisons among different methods showed that high-degree association retrieval did not perform significantly better than the association mining method or the direct retrieval method in our test-bed.
Artificial Intelligence Lab, The Department of Management Information Systems, The University of Arizona, Rm. 430, McClelland Hall, 1130 E. Helen Street, Tucson, AZ 85721
year
2004
journal
Journal of the American Society for Information Science and Technology
%0 Journal Article
%1 citeulike:3738166
%A Huang, Zan
%A Chung, Wingyan
%A Chen, Hsinchun
%C Artificial Intelligence Lab, The Department of Management Information Systems, The University of Arizona, Rm. 430, McClelland Hall, 1130 E. Helen Street, Tucson, AZ 85721
%D 2004
%J Journal of the American Society for Information Science and Technology
%K recommender spread-activation
%N 3
%P 259--274
%R 10.1002/asi.10372
%T A graph model for E-commerce recommender systems
%U http://dx.doi.org/10.1002/asi.10372
%V 55
%X Information overload on the Web has created enormous challenges to customers selecting products for online purchases and to online businesses attempting to identify customers' preferences efficiently. Various recommender systems employing different data representations and recommendation methods are currently used to address these challenges. In this research, we developed a graph model that provides a generic data representation and can support different recommendation methods. To demonstrate its usefulness and flexibility, we developed three recommendation methods: direct retrieval, association mining, and high-degree association retrieval. We used a data set from an online bookstore as our research test-bed. Evaluation results showed that combining product content information and historical customer transaction information achieved more accurate predictions and relevant recommendations than using only collaborative information. However, comparisons among different methods showed that high-degree association retrieval did not perform significantly better than the association mining method or the direct retrieval method in our test-bed.
@article{citeulike:3738166,
abstract = {Information overload on the Web has created enormous challenges to customers selecting products for online purchases and to online businesses attempting to identify customers' preferences efficiently. Various recommender systems employing different data representations and recommendation methods are currently used to address these challenges. In this research, we developed a graph model that provides a generic data representation and can support different recommendation methods. To demonstrate its usefulness and flexibility, we developed three recommendation methods: direct retrieval, association mining, and high-degree association retrieval. We used a data set from an online bookstore as our research test-bed. Evaluation results showed that combining product content information and historical customer transaction information achieved more accurate predictions and relevant recommendations than using only collaborative information. However, comparisons among different methods showed that high-degree association retrieval did not perform significantly better than the association mining method or the direct retrieval method in our test-bed.},
added-at = {2009-07-01T11:12:30.000+0200},
address = {Artificial Intelligence Lab, The Department of Management Information Systems, The University of Arizona, Rm. 430, McClelland Hall, 1130 E. Helen Street, Tucson, AZ 85721},
author = {Huang, Zan and Chung, Wingyan and Chen, Hsinchun},
biburl = {https://www.bibsonomy.org/bibtex/2c907eeaac191524506ffc23021fe06a9/brusilovsky},
citeulike-article-id = {3738166},
doi = {10.1002/asi.10372},
interhash = {ec75581e21d5c5e9ca3ea4ca6752ad50},
intrahash = {c907eeaac191524506ffc23021fe06a9},
journal = {Journal of the American Society for Information Science and Technology},
keywords = {recommender spread-activation},
number = 3,
pages = {259--274},
posted-at = {2008-12-02 23:21:52},
priority = {2},
timestamp = {2009-07-01T11:12:34.000+0200},
title = {A graph model for E-commerce recommender systems},
url = {http://dx.doi.org/10.1002/asi.10372},
volume = 55,
year = 2004
}