Search queries are appropriate when users have explicit intent, but they perform poorly when the intent is difficult to express or if the user is simply looking to be inspired. Visual browsing systems allow e-commerce platforms to address these scenarios while offering the user an engaging shopping experience. Here we explore extensions in the direction of adaptive personalization and item diversification within Stream, a new form of visual browsing and discovery by Amazon. Our system presents the user with a diverse set of interesting items while adapting to user interactions. Our solution consists of three components (1) a Bayesian regression model for scoring the relevance of items while leveraging uncertainty, (2) a submodular diversification framework that re-ranks the top scoring items based on category, and (3) personalized category preferences learned from the user's behavior. When tested on live traffic, our algorithms show a strong lift in click-through-rate and session duration.
%0 Conference Paper
%1 citeulike:14139131
%A Teo, Choon H.
%A Nassif, Houssam
%A Hill, Daniel
%A Srinivasan, Sriram
%A Goodman, Mitchell
%A Mohan, Vijai
%A Vishwanathan, S. V. N.
%B Proceedings of the 10th ACM Conference on Recommender Systems
%C New York, NY, USA
%D 2016
%I ACM
%K adaptive-interface diversity recommender recsys2016
%P 35--38
%R 10.1145/2959100.2959171
%T Adaptive, Personalized Diversity for Visual Discovery
%U http://dx.doi.org/10.1145/2959100.2959171
%X Search queries are appropriate when users have explicit intent, but they perform poorly when the intent is difficult to express or if the user is simply looking to be inspired. Visual browsing systems allow e-commerce platforms to address these scenarios while offering the user an engaging shopping experience. Here we explore extensions in the direction of adaptive personalization and item diversification within Stream, a new form of visual browsing and discovery by Amazon. Our system presents the user with a diverse set of interesting items while adapting to user interactions. Our solution consists of three components (1) a Bayesian regression model for scoring the relevance of items while leveraging uncertainty, (2) a submodular diversification framework that re-ranks the top scoring items based on category, and (3) personalized category preferences learned from the user's behavior. When tested on live traffic, our algorithms show a strong lift in click-through-rate and session duration.
%@ 978-1-4503-4035-9
@inproceedings{citeulike:14139131,
abstract = {{Search queries are appropriate when users have explicit intent, but they perform poorly when the intent is difficult to express or if the user is simply looking to be inspired. Visual browsing systems allow e-commerce platforms to address these scenarios while offering the user an engaging shopping experience. Here we explore extensions in the direction of adaptive personalization and item diversification within Stream, a new form of visual browsing and discovery by Amazon. Our system presents the user with a diverse set of interesting items while adapting to user interactions. Our solution consists of three components (1) a Bayesian regression model for scoring the relevance of items while leveraging uncertainty, (2) a submodular diversification framework that re-ranks the top scoring items based on category, and (3) personalized category preferences learned from the user's behavior. When tested on live traffic, our algorithms show a strong lift in click-through-rate and session duration.}},
added-at = {2018-03-19T12:24:51.000+0100},
address = {New York, NY, USA},
author = {Teo, Choon H. and Nassif, Houssam and Hill, Daniel and Srinivasan, Sriram and Goodman, Mitchell and Mohan, Vijai and Vishwanathan, S. V. N.},
biburl = {https://www.bibsonomy.org/bibtex/299c3448798a1401b335c75891dc7842b/aho},
booktitle = {Proceedings of the 10th ACM Conference on Recommender Systems},
citeulike-article-id = {14139131},
citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=2959171},
citeulike-linkout-1 = {http://dx.doi.org/10.1145/2959100.2959171},
doi = {10.1145/2959100.2959171},
interhash = {eb2c8479e1e0e71f7ad4ae06bb0a87e9},
intrahash = {99c3448798a1401b335c75891dc7842b},
isbn = {978-1-4503-4035-9},
keywords = {adaptive-interface diversity recommender recsys2016},
location = {Boston, Massachusetts, USA},
pages = {35--38},
posted-at = {2016-09-17 17:03:26},
priority = {2},
publisher = {ACM},
series = {RecSys '16},
timestamp = {2018-03-19T12:24:51.000+0100},
title = {{Adaptive, Personalized Diversity for Visual Discovery}},
url = {http://dx.doi.org/10.1145/2959100.2959171},
year = 2016
}