User-system interaction in recommender systems involves three aspects: temporal browsing (viewing recommendation lists and/or searching/fltering), 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 efects of these assumptions along three dimensions in eight diferent 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, fnding that this new model outperforms the others.
|Original language||English (US)|
|Title of host publication||RecSys 2019 - 13th ACM Conference on Recommender Systems|
|Publisher||Association for Computing Machinery, Inc|
|Number of pages||5|
|State||Published - Sep 10 2019|
|Event||13th ACM Conference on Recommender Systems, RecSys 2019 - Copenhagen, Denmark|
Duration: Sep 16 2019 → Sep 20 2019
|Name||RecSys 2019 - 13th ACM Conference on Recommender Systems|
|Conference||13th ACM Conference on Recommender Systems, RecSys 2019|
|Period||9/16/19 → 9/20/19|
Bibliographical noteFunding Information:
This work was supported by the National Science Foundation under grant IIS-1319382. The frst author was also supported by the Doctoral Dissertation Fellowship, 2016-17, by the Graduate School at the University of Minnesota.
- Decision feld theory
- Decision making
- Recurrent neural networks