From preference into decision making: modeling user interactions in recommender systems

Qian Zhao, Martijn C. Willemsen, Gediminas Adomavicius, F. Maxwell Harper, Joseph A. Konstan

Onderzoeksoutput: Hoofdstuk in Boek/Rapport/CongresprocedureConferentiebijdrageAcademicpeer review

1 Citaat (Scopus)

Samenvatting

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.
Originele taal-2Engels
TitelRecSys 2019 - 13th ACM Conference on Recommender Systems
Plaats van productieNew York
UitgeverijAssociation for Computing Machinery, Inc
Pagina's29-33
Aantal pagina's5
ISBN van elektronische versie9781450362436
ISBN van geprinte versie978-1-4503-6243-6
DOI's
StatusGepubliceerd - 10 sep 2019
EvenementRecSys '19 ACM Conference on Recommender Systems - Copenhagen, Denemarken
Duur: 16 sep 201920 sep 2019

Congres

CongresRecSys '19 ACM Conference on Recommender Systems
LandDenemarken
StadCopenhagen
Periode16/09/1920/09/19

Trefwoorden

  • decision field theory, decision making, recurrent neural networks

Vingerafdruk Duik in de onderzoeksthema's van 'From preference into decision making: modeling user interactions in recommender systems'. Samen vormen ze een unieke vingerafdruk.

  • Citeer dit

    Zhao, Q., Willemsen, M. C., Adomavicius, G., Harper, F. M., & Konstan, J. A. (2019). From preference into decision making: modeling user interactions in recommender systems. In RecSys 2019 - 13th ACM Conference on Recommender Systems (blz. 29-33). Association for Computing Machinery, Inc. https://doi.org/10.1145/3298689.3347065