TBPR: trinity preference based Bayesian personalized ranking for multivariate implicit feedback

Huihuai Qiu; Guibing Guo; Jie Zhang; Zhu Sun; Hai Thanh Nguyen; Yun Liu

doi:10.1145/2930238.2930272

TBPR: trinity preference based Bayesian personalized ranking for multivariate implicit feedback

Huihuai Qiu^*, Guibing Guo, Jie Zhang, Zhu Sun, Hai Thanh Nguyen, Yun Liu

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference abstract › peer-review

15 Citations (Scopus)

Abstract

In e-commerce systems, user preference can be inferred from multivariate implicit feedback (i.e., actions). However, most methods merely focus on homogeneous implicit feedback (i.e., purchase). In this paper, we adopt another two typical actions, i.e., view and like, as auxiliaries to enhance purchase recommendation, whereby a trinity Bayesian personalized ranking (TBPR) method is proposed. Specifically, we introduce trinity preference to investigate the difference of users' preference among three types of items: 1) items with purchase action; 2) items with only auxiliary actions; 3) items without any action. Empirical study on the realworld dataset demonstrates that our method significantly outperforms state-of-the-art algorithms.

Original language	English
Title of host publication	UMAP 2016
Subtitle of host publication	Proceedings of the 2016 Conference on User Modeling Adaptation and Personalization
Place of Publication	New York
Publisher	Association for Computing Machinery, Inc
Pages	305-306
Number of pages	2
ISBN (Electronic)	9781450343701
DOIs	https://doi.org/10.1145/2930238.2930272
Publication status	Published - 2016
Externally published	Yes
Event	24th ACM International Conference on User Modeling, Adaptation, and Personalization, UMAP 2016 - Halifax, Canada Duration: 13 Jul 2016 → 17 Jul 2016

Conference

Conference	24th ACM International Conference on User Modeling, Adaptation, and Personalization, UMAP 2016
Country/Territory	Canada
City	Halifax
Period	13/07/16 → 17/07/16

Keywords

Implicit feedback
Recommendation
Trinity preference

Access to Document

10.1145/2930238.2930272

Cite this

@inbook{c81ccc1165464a28b77c10d2bed6867a,

title = "TBPR: trinity preference based Bayesian personalized ranking for multivariate implicit feedback",

abstract = "In e-commerce systems, user preference can be inferred from multivariate implicit feedback (i.e., actions). However, most methods merely focus on homogeneous implicit feedback (i.e., purchase). In this paper, we adopt another two typical actions, i.e., view and like, as auxiliaries to enhance purchase recommendation, whereby a trinity Bayesian personalized ranking (TBPR) method is proposed. Specifically, we introduce trinity preference to investigate the difference of users' preference among three types of items: 1) items with purchase action; 2) items with only auxiliary actions; 3) items without any action. Empirical study on the realworld dataset demonstrates that our method significantly outperforms state-of-the-art algorithms.",

keywords = "Implicit feedback, Recommendation, Trinity preference",

author = "Huihuai Qiu and Guibing Guo and Jie Zhang and Zhu Sun and Nguyen, {Hai Thanh} and Yun Liu",

year = "2016",

doi = "10.1145/2930238.2930272",

language = "English",

pages = "305--306",

booktitle = "UMAP 2016",

publisher = "Association for Computing Machinery, Inc",

note = "24th ACM International Conference on User Modeling, Adaptation, and Personalization, UMAP 2016 ; Conference date: 13-07-2016 Through 17-07-2016",

}

Qiu, H, Guo, G, Zhang, J, Sun, Z, Nguyen, HT & Liu, Y 2016, TBPR: trinity preference based Bayesian personalized ranking for multivariate implicit feedback. in UMAP 2016: Proceedings of the 2016 Conference on User Modeling Adaptation and Personalization. Association for Computing Machinery, Inc, New York, pp. 305-306, 24th ACM International Conference on User Modeling, Adaptation, and Personalization, UMAP 2016, Halifax, Canada, 13/07/16. https://doi.org/10.1145/2930238.2930272

TBPR: trinity preference based Bayesian personalized ranking for multivariate implicit feedback. / Qiu, Huihuai; Guo, Guibing; Zhang, Jie et al.
UMAP 2016: Proceedings of the 2016 Conference on User Modeling Adaptation and Personalization. New York: Association for Computing Machinery, Inc, 2016. p. 305-306.

Research output: Chapter in Book/Report/Conference proceeding › Conference abstract › peer-review

TY - CHAP

T1 - TBPR

T2 - 24th ACM International Conference on User Modeling, Adaptation, and Personalization, UMAP 2016

AU - Qiu, Huihuai

AU - Guo, Guibing

AU - Zhang, Jie

AU - Sun, Zhu

AU - Nguyen, Hai Thanh

AU - Liu, Yun

PY - 2016

Y1 - 2016

N2 - In e-commerce systems, user preference can be inferred from multivariate implicit feedback (i.e., actions). However, most methods merely focus on homogeneous implicit feedback (i.e., purchase). In this paper, we adopt another two typical actions, i.e., view and like, as auxiliaries to enhance purchase recommendation, whereby a trinity Bayesian personalized ranking (TBPR) method is proposed. Specifically, we introduce trinity preference to investigate the difference of users' preference among three types of items: 1) items with purchase action; 2) items with only auxiliary actions; 3) items without any action. Empirical study on the realworld dataset demonstrates that our method significantly outperforms state-of-the-art algorithms.

AB - In e-commerce systems, user preference can be inferred from multivariate implicit feedback (i.e., actions). However, most methods merely focus on homogeneous implicit feedback (i.e., purchase). In this paper, we adopt another two typical actions, i.e., view and like, as auxiliaries to enhance purchase recommendation, whereby a trinity Bayesian personalized ranking (TBPR) method is proposed. Specifically, we introduce trinity preference to investigate the difference of users' preference among three types of items: 1) items with purchase action; 2) items with only auxiliary actions; 3) items without any action. Empirical study on the realworld dataset demonstrates that our method significantly outperforms state-of-the-art algorithms.

KW - Implicit feedback

KW - Recommendation

KW - Trinity preference

UR - http://www.scopus.com/inward/record.url?scp=84984889767&partnerID=8YFLogxK

U2 - 10.1145/2930238.2930272

DO - 10.1145/2930238.2930272

M3 - Conference abstract

AN - SCOPUS:84984889767

SP - 305

EP - 306

BT - UMAP 2016

PB - Association for Computing Machinery, Inc

CY - New York

Y2 - 13 July 2016 through 17 July 2016

ER -

TBPR: trinity preference based Bayesian personalized ranking for multivariate implicit feedback

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this