Diversified utility maximization for recommendations

Azin Ashkan; Branislav Kveton; Shlomo Berkovsky; Zheng Wen

Diversified utility maximization for recommendations

Azin Ashkan, Branislav Kveton, Shlomo Berkovsky, Zheng Wen

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

Abstract

Consider the problem of recommending items to a group of users subject to the diversity of their tastes. The goal is to recommend a list of items, such that the interests of each user are covered. We cast this problem as maximizing a diversified utility function of the group, the optimal solution of which can be found greedily. We conduct a user study in order to evaluate the performance of the proposed method. Evaluation results show that our method represents an effective strategy compared to various settings in which a convex combination of utility and diversity is maximized.

Original language	English
Title of host publication	Poster-RecSys 2014
Subtitle of host publication	Poster Proceedings of the 8th ACM Conference on Recommender Systems (RecSys 2014)
Editors	Li Chen, Jalal Mahmud
Publisher	CEUR Workshop Proceedings
Number of pages	2
Publication status	Published - 2014
Externally published	Yes
Event	8th ACM Conference on Recommender Systems, RecSys 2014 - Silicon Valley, United States Duration: 6 Oct 2014 → 10 Oct 2014

Conference

Conference	8th ACM Conference on Recommender Systems, RecSys 2014
Country/Territory	United States
City	Silicon Valley
Period	6/10/14 → 10/10/14

Cite this

@inproceedings{a82cb99852c94dee9495439145b667b5,

title = "Diversified utility maximization for recommendations",

abstract = "Consider the problem of recommending items to a group of users subject to the diversity of their tastes. The goal is to recommend a list of items, such that the interests of each user are covered. We cast this problem as maximizing a diversified utility function of the group, the optimal solution of which can be found greedily. We conduct a user study in order to evaluate the performance of the proposed method. Evaluation results show that our method represents an effective strategy compared to various settings in which a convex combination of utility and diversity is maximized.",

author = "Azin Ashkan and Branislav Kveton and Shlomo Berkovsky and Zheng Wen",

year = "2014",

language = "English",

editor = "Li Chen and Jalal Mahmud",

booktitle = "Poster-RecSys 2014",

publisher = "CEUR Workshop Proceedings",

note = "8th ACM Conference on Recommender Systems, RecSys 2014 ; Conference date: 06-10-2014 Through 10-10-2014",

}

Diversified utility maximization for recommendations. / Ashkan, Azin; Kveton, Branislav; Berkovsky, Shlomo et al.
Poster-RecSys 2014: Poster Proceedings of the 8th ACM Conference on Recommender Systems (RecSys 2014). ed. / Li Chen; Jalal Mahmud. CEUR Workshop Proceedings, 2014.

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

TY - GEN

T1 - Diversified utility maximization for recommendations

AU - Ashkan, Azin

AU - Kveton, Branislav

AU - Berkovsky, Shlomo

AU - Wen, Zheng

PY - 2014

Y1 - 2014

N2 - Consider the problem of recommending items to a group of users subject to the diversity of their tastes. The goal is to recommend a list of items, such that the interests of each user are covered. We cast this problem as maximizing a diversified utility function of the group, the optimal solution of which can be found greedily. We conduct a user study in order to evaluate the performance of the proposed method. Evaluation results show that our method represents an effective strategy compared to various settings in which a convex combination of utility and diversity is maximized.

AB - Consider the problem of recommending items to a group of users subject to the diversity of their tastes. The goal is to recommend a list of items, such that the interests of each user are covered. We cast this problem as maximizing a diversified utility function of the group, the optimal solution of which can be found greedily. We conduct a user study in order to evaluate the performance of the proposed method. Evaluation results show that our method represents an effective strategy compared to various settings in which a convex combination of utility and diversity is maximized.

UR - http://ceur-ws.org/Vol-1247/

UR - http://www.scopus.com/inward/record.url?scp=84913573320&partnerID=8YFLogxK

M3 - Conference proceeding contribution

BT - Poster-RecSys 2014

A2 - Chen, Li

A2 - Mahmud, Jalal

PB - CEUR Workshop Proceedings

T2 - 8th ACM Conference on Recommender Systems, RecSys 2014

Y2 - 6 October 2014 through 10 October 2014

ER -

Diversified utility maximization for recommendations

Abstract

Conference

Other files and links

Fingerprint

Cite this