%0 Conference Paper %1 Zhao:2019:PDM:3298689.3347065 %A Zhao, Qian %A Willemsen, Martijn C. %A Adomavicius, Gediminas %A Harper, F. Maxwell %A Konstan, Joseph A. %B Proceedings of the 13th ACM Conference on Recommender Systems %C New York, NY, USA %D 2019 %I ACM %K decision-making interaction-modeling recommender %P 29--33 %R 10.1145/3298689.3347065 %T From Preference into Decision Making: Modeling User Interactions in Recommender Systems %U http://doi.acm.org/10.1145/3298689.3347065 %X User-system interaction in recommender systems involves three aspects: temporal browsing (viewing recommendation lists and/or searching/filtering), action (performing actions on recommended items, e.g., clicking, consuming) and inaction (neglecting or skipping recommended items). Modern recommenders build machine learning models from recordings of such user interaction with the system, and in doing so they commonly make certain assumptions (e.g., pairwise preference orders, independent or competitive probabilistic choices, etc.). In this paper, we set out to study the effects of these assumptions along three dimensions in eight different single models and three associated hybrid models on a user browsing data set collected from a real-world recommender system application. We further design a novel model based on recurrent neural networks and multi-task learning, inspired by Decision Field Theory, a model of human decision making. We report on precision, recall, and MAP, finding that this new model outperforms the others. %@ 978-1-4503-6243-6

@inproceedings{Zhao:2019:PDM:3298689.3347065, abstract = {User-system interaction in recommender systems involves three aspects: temporal browsing (viewing recommendation lists and/or searching/filtering), action (performing actions on recommended items, e.g., clicking, consuming) and inaction (neglecting or skipping recommended items). Modern recommenders build machine learning models from recordings of such user interaction with the system, and in doing so they commonly make certain assumptions (e.g., pairwise preference orders, independent or competitive probabilistic choices, etc.). In this paper, we set out to study the effects of these assumptions along three dimensions in eight different single models and three associated hybrid models on a user browsing data set collected from a real-world recommender system application. We further design a novel model based on recurrent neural networks and multi-task learning, inspired by Decision Field Theory, a model of human decision making. We report on precision, recall, and MAP, finding that this new model outperforms the others.}, acmid = {3347065}, added-at = {2019-09-16T12:01:27.000+0200}, address = {New York, NY, USA}, author = {Zhao, Qian and Willemsen, Martijn C. and Adomavicius, Gediminas and Harper, F. Maxwell and Konstan, Joseph A.}, biburl = {https://www.bibsonomy.org/bibtex/2c1bdb9a53b9f8db356a86efb297f3fff/brusilovsky}, booktitle = {Proceedings of the 13th ACM Conference on Recommender Systems}, description = {From preference into decision making}, doi = {10.1145/3298689.3347065}, interhash = {481a0d95b0638595f7a8637dc28df5b1}, intrahash = {c1bdb9a53b9f8db356a86efb297f3fff}, isbn = {978-1-4503-6243-6}, keywords = {decision-making interaction-modeling recommender}, location = {Copenhagen, Denmark}, numpages = {5}, pages = {29--33}, publisher = {ACM}, series = {RecSys '19}, timestamp = {2023-06-05T01:22:37.000+0200}, title = {From Preference into Decision Making: Modeling User Interactions in Recommender Systems}, url = {http://doi.acm.org/10.1145/3298689.3347065}, year = 2019 }