Please use this identifier to cite or link to this item: https://doi.org/10.1145/3209219.3209235
Title: Collaborative filtering with behavioral models
Authors: Sovilj D.
Sanner S.
Soh H. 
Li H.
Keywords: Bayesian model averaging
Behavioral modeling
Collaborative iltering
Issue Date: 2018
Publisher: Association for Computing Machinery, Inc
Citation: Sovilj D., Sanner S., Soh H., Li H. (2018). Collaborative filtering with behavioral models. UMAP 2018 - Proceedings of the 26th Conference on User Modeling, Adaptation and Personalization : 91-99. ScholarBank@NUS Repository. https://doi.org/10.1145/3209219.3209235
Abstract: Collaborative iltering (CF) has made it possible to build personalized recommendation models leveraging the collective data of large user groups, albeit with prescribed models that cannot easily leverage the existence of known behavioral models in particular settings. In this paper, we facilitate the combination of CF with existing behavioral models by introducing Bayesian Behavioral Collaborative Filtering (BBCF). BBCF works by embedding arbitrary (black-box) probabilistic models of human behavior in a latent variable Bayesian framework capable of collectively leveraging behavioral models trained on all users for personalized recommendation. There are three key advantages of BBCF compared to traditional CF and non- CF methods: (1) BBCF can leverage highly specialized behavioral models for speciic CF use cases that may outperform existing generic models used in standard CF, (2) the behavioral models used in BBCF may ofer enhanced intepretability and explainability compared to generic CF methods, and (3) compared to non-CF methods that would train a behavioral model per speciic user and thus may sufer when individual user data is limited, BBCF leverages the data of all users thus enabling strong performance across the data availability spectrum including the near cold-start case. Experimentally, we compare BBCF to individual and global behavioral models as well as CF techniques; our evaluation domains span sequential and non-sequential tasks with a range of behavioral models for individual users, tasks, or goal-oriented behavior. Our results demonstrate that BBCF is competitive if not better than existing methods while still ofering the interpretability and explainability beneits intrinsic to many behavioral models. ? 2018 Association for Computing Machinery.
Source Title: UMAP 2018 - Proceedings of the 26th Conference on User Modeling, Adaptation and Personalization
URI: http://scholarbank.nus.edu.sg/handle/10635/152219
ISBN: 9.78E+12
DOI: 10.1145/3209219.3209235
Appears in Collections:Staff Publications
Elements

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
p91-sovilj.pdf657.6 kBAdobe PDF

OPEN

NoneView/Download

Page view(s)

5
checked on Apr 21, 2019

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.