%0 Conference Paper %1 citeulike:14142467 %A Wu, Chao Y. %A Alvino, Christopher V. %A Smola, Alexander J. %A Basilico, Justin %B Proceedings of the 10th ACM Conference on Recommender Systems %C New York, NY, USA %D 2016 %I ACM %K adaptive-hypermedia navigation recommender recsys2016 user-modeling %P 341--348 %R 10.1145/2959100.2959174 %T Using Navigation to Improve Recommendations in Real-Time %U http://dx.doi.org/10.1145/2959100.2959174 %X Implicit feedback is a key source of information for many recommendation and personalization approaches. However, using it typically requires multiple episodes of interaction and roundtrips to a recommendation engine. This adds latency and neglects the opportunity of immediate personalization for a user while the user is navigating recommendations. We propose a novel strategy to address the above problem in a principled manner. The key insight is that as we observe a user's interactions, it reveals much more information about her desires. We exploit this by inferring the within-session user intent on-the-fly based on navigation interactions, since they offer valuable clues into a user's current state of mind. Using navigation patterns and adapting recommendations in real-time creates an opportunity to provide more accurate recommendations. By prefetching a larger amount of content, this can be carried out entirely in the client (such as a browser) without added latency. We define a new Bayesian model with an efficient inference algorithm. We demonstrate significant improvements with this novel approach on a real-world, large-scale dataset from Netflix on the problem of adapting the recommendations on a user's homepage. %@ 978-1-4503-4035-9

@inproceedings{citeulike:14142467, abstract = {{Implicit feedback is a key source of information for many recommendation and personalization approaches. However, using it typically requires multiple episodes of interaction and roundtrips to a recommendation engine. This adds latency and neglects the opportunity of immediate personalization for a user while the user is navigating recommendations. We propose a novel strategy to address the above problem in a principled manner. The key insight is that as we observe a user's interactions, it reveals much more information about her desires. We exploit this by inferring the within-session user intent on-the-fly based on navigation interactions, since they offer valuable clues into a user's current state of mind. Using navigation patterns and adapting recommendations in real-time creates an opportunity to provide more accurate recommendations. By prefetching a larger amount of content, this can be carried out entirely in the client (such as a browser) without added latency. We define a new Bayesian model with an efficient inference algorithm. We demonstrate significant improvements with this novel approach on a real-world, large-scale dataset from Netflix on the problem of adapting the recommendations on a user's homepage.}}, added-at = {2018-03-19T12:24:51.000+0100}, address = {New York, NY, USA}, author = {Wu, Chao Y. and Alvino, Christopher V. and Smola, Alexander J. and Basilico, Justin}, biburl = {https://www.bibsonomy.org/bibtex/28d193c674812e05fb9b9a0551df3103e/aho}, booktitle = {Proceedings of the 10th ACM Conference on Recommender Systems}, citeulike-article-id = {14142467}, citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=2959174}, citeulike-linkout-1 = {http://dx.doi.org/10.1145/2959100.2959174}, doi = {10.1145/2959100.2959174}, interhash = {7be547b6ed25883e73ffec12df99aa1e}, intrahash = {8d193c674812e05fb9b9a0551df3103e}, isbn = {978-1-4503-4035-9}, keywords = {adaptive-hypermedia navigation recommender recsys2016 user-modeling}, location = {Boston, Massachusetts, USA}, pages = {341--348}, posted-at = {2016-09-19 16:32:31}, priority = {2}, publisher = {ACM}, series = {RecSys '16}, timestamp = {2018-03-19T12:24:51.000+0100}, title = {{Using Navigation to Improve Recommendations in Real-Time}}, url = {http://dx.doi.org/10.1145/2959100.2959174}, year = 2016 }