Loading…

Generating top-k packages via preference elicitation

There are several applications, such as play lists of songs or movies, and shopping carts, where users are interested in finding top- k packages, consisting of sets of items. In response to this need, there has been a recent flurry of activity around extending classical recommender systems (RS), whi...

Full description

Saved in:
Bibliographic Details
Published in:Proceedings of the VLDB Endowment 2014-10, Vol.7 (14), p.1941-1952
Main Authors: Xie, Min, Lakshmanan, Laks V. S., Wood, Peter T.
Format: Article
Language:English
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by cdi_FETCH-LOGICAL-c285t-b3b5f833ddfede4b7a7bd1a1d3db10bf34d313b36827c0100a6cb01e026954e63
cites cdi_FETCH-LOGICAL-c285t-b3b5f833ddfede4b7a7bd1a1d3db10bf34d313b36827c0100a6cb01e026954e63
container_end_page 1952
container_issue 14
container_start_page 1941
container_title Proceedings of the VLDB Endowment
container_volume 7
creator Xie, Min
Lakshmanan, Laks V. S.
Wood, Peter T.
description There are several applications, such as play lists of songs or movies, and shopping carts, where users are interested in finding top- k packages, consisting of sets of items. In response to this need, there has been a recent flurry of activity around extending classical recommender systems (RS), which are effective at recommending individual items, to recommend packages, or sets of items. The few recent proposals for package RS suffer from one of the following drawbacks: they either rely on hard constraints which may be difficult to be specified exactly by the user or on returning Pareto-optimal packages which are too numerous for the user to sift through. To overcome these limitations, we propose an alternative approach for finding personalized top- k packages for users, by capturing users' preferences over packages using a linear utility function which the system learns. Instead of asking a user to specify this function explicitly, which is unrealistic, we explicitly model the uncertainty in the utility function and propose a preference elicitation-based framework for learning the utility function through feedback provided by the user. We propose several sampling-based methods which, given user feedback, can capture the updated utility function. We develop an efficient algorithm for generating top- k packages using the learned utility function, where the rank ordering respects any of a variety of ranking semantics proposed in the literature. Through extensive experiments on both real and synthetic datasets, we demonstrate the efficiency and effectiveness of the proposed system for finding top- k packages.
doi_str_mv 10.14778/2733085.2733099
format article
fullrecord <record><control><sourceid>crossref</sourceid><recordid>TN_cdi_crossref_primary_10_14778_2733085_2733099</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>10_14778_2733085_2733099</sourcerecordid><originalsourceid>FETCH-LOGICAL-c285t-b3b5f833ddfede4b7a7bd1a1d3db10bf34d313b36827c0100a6cb01e026954e63</originalsourceid><addsrcrecordid>eNpNj0tLw0AUhQexYG3du8wfSL03d15ZStEqFNzoOszjpsTWJMwEwX9vqVm4-s7icDifEPcIG5TG2IfKEIFVmwvr-kosK1RQWqjN9b98I25z_gTQVqNdCrnjnpObuv5QTMNYHovRhaM7cC6-O1eMiVtO3Acu-NSFbjo3h34tFq07Zb6buRIfz0_v25dy_7Z73T7uy1BZNZWevGotUYwtR5beOOMjOowUPYJvSUZC8qRtZQIggNPBAzJUulaSNa0E_O2GNOR8vtKMqfty6adBaC7WzWzdzNb0C9j2Shg</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Generating top-k packages via preference elicitation</title><source>Association for Computing Machinery:Jisc Collections:ACM OPEN Journals 2023-2025 (reading list)</source><creator>Xie, Min ; Lakshmanan, Laks V. S. ; Wood, Peter T.</creator><creatorcontrib>Xie, Min ; Lakshmanan, Laks V. S. ; Wood, Peter T.</creatorcontrib><description>There are several applications, such as play lists of songs or movies, and shopping carts, where users are interested in finding top- k packages, consisting of sets of items. In response to this need, there has been a recent flurry of activity around extending classical recommender systems (RS), which are effective at recommending individual items, to recommend packages, or sets of items. The few recent proposals for package RS suffer from one of the following drawbacks: they either rely on hard constraints which may be difficult to be specified exactly by the user or on returning Pareto-optimal packages which are too numerous for the user to sift through. To overcome these limitations, we propose an alternative approach for finding personalized top- k packages for users, by capturing users' preferences over packages using a linear utility function which the system learns. Instead of asking a user to specify this function explicitly, which is unrealistic, we explicitly model the uncertainty in the utility function and propose a preference elicitation-based framework for learning the utility function through feedback provided by the user. We propose several sampling-based methods which, given user feedback, can capture the updated utility function. We develop an efficient algorithm for generating top- k packages using the learned utility function, where the rank ordering respects any of a variety of ranking semantics proposed in the literature. Through extensive experiments on both real and synthetic datasets, we demonstrate the efficiency and effectiveness of the proposed system for finding top- k packages.</description><identifier>ISSN: 2150-8097</identifier><identifier>EISSN: 2150-8097</identifier><identifier>DOI: 10.14778/2733085.2733099</identifier><language>eng</language><ispartof>Proceedings of the VLDB Endowment, 2014-10, Vol.7 (14), p.1941-1952</ispartof><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c285t-b3b5f833ddfede4b7a7bd1a1d3db10bf34d313b36827c0100a6cb01e026954e63</citedby><cites>FETCH-LOGICAL-c285t-b3b5f833ddfede4b7a7bd1a1d3db10bf34d313b36827c0100a6cb01e026954e63</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,780,784,27922,27923</link.rule.ids></links><search><creatorcontrib>Xie, Min</creatorcontrib><creatorcontrib>Lakshmanan, Laks V. S.</creatorcontrib><creatorcontrib>Wood, Peter T.</creatorcontrib><title>Generating top-k packages via preference elicitation</title><title>Proceedings of the VLDB Endowment</title><description>There are several applications, such as play lists of songs or movies, and shopping carts, where users are interested in finding top- k packages, consisting of sets of items. In response to this need, there has been a recent flurry of activity around extending classical recommender systems (RS), which are effective at recommending individual items, to recommend packages, or sets of items. The few recent proposals for package RS suffer from one of the following drawbacks: they either rely on hard constraints which may be difficult to be specified exactly by the user or on returning Pareto-optimal packages which are too numerous for the user to sift through. To overcome these limitations, we propose an alternative approach for finding personalized top- k packages for users, by capturing users' preferences over packages using a linear utility function which the system learns. Instead of asking a user to specify this function explicitly, which is unrealistic, we explicitly model the uncertainty in the utility function and propose a preference elicitation-based framework for learning the utility function through feedback provided by the user. We propose several sampling-based methods which, given user feedback, can capture the updated utility function. We develop an efficient algorithm for generating top- k packages using the learned utility function, where the rank ordering respects any of a variety of ranking semantics proposed in the literature. Through extensive experiments on both real and synthetic datasets, we demonstrate the efficiency and effectiveness of the proposed system for finding top- k packages.</description><issn>2150-8097</issn><issn>2150-8097</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2014</creationdate><recordtype>article</recordtype><recordid>eNpNj0tLw0AUhQexYG3du8wfSL03d15ZStEqFNzoOszjpsTWJMwEwX9vqVm4-s7icDifEPcIG5TG2IfKEIFVmwvr-kosK1RQWqjN9b98I25z_gTQVqNdCrnjnpObuv5QTMNYHovRhaM7cC6-O1eMiVtO3Acu-NSFbjo3h34tFq07Zb6buRIfz0_v25dy_7Z73T7uy1BZNZWevGotUYwtR5beOOMjOowUPYJvSUZC8qRtZQIggNPBAzJUulaSNa0E_O2GNOR8vtKMqfty6adBaC7WzWzdzNb0C9j2Shg</recordid><startdate>201410</startdate><enddate>201410</enddate><creator>Xie, Min</creator><creator>Lakshmanan, Laks V. S.</creator><creator>Wood, Peter T.</creator><scope>AAYXX</scope><scope>CITATION</scope></search><sort><creationdate>201410</creationdate><title>Generating top-k packages via preference elicitation</title><author>Xie, Min ; Lakshmanan, Laks V. S. ; Wood, Peter T.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c285t-b3b5f833ddfede4b7a7bd1a1d3db10bf34d313b36827c0100a6cb01e026954e63</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2014</creationdate><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Xie, Min</creatorcontrib><creatorcontrib>Lakshmanan, Laks V. S.</creatorcontrib><creatorcontrib>Wood, Peter T.</creatorcontrib><collection>CrossRef</collection><jtitle>Proceedings of the VLDB Endowment</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Xie, Min</au><au>Lakshmanan, Laks V. S.</au><au>Wood, Peter T.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Generating top-k packages via preference elicitation</atitle><jtitle>Proceedings of the VLDB Endowment</jtitle><date>2014-10</date><risdate>2014</risdate><volume>7</volume><issue>14</issue><spage>1941</spage><epage>1952</epage><pages>1941-1952</pages><issn>2150-8097</issn><eissn>2150-8097</eissn><abstract>There are several applications, such as play lists of songs or movies, and shopping carts, where users are interested in finding top- k packages, consisting of sets of items. In response to this need, there has been a recent flurry of activity around extending classical recommender systems (RS), which are effective at recommending individual items, to recommend packages, or sets of items. The few recent proposals for package RS suffer from one of the following drawbacks: they either rely on hard constraints which may be difficult to be specified exactly by the user or on returning Pareto-optimal packages which are too numerous for the user to sift through. To overcome these limitations, we propose an alternative approach for finding personalized top- k packages for users, by capturing users' preferences over packages using a linear utility function which the system learns. Instead of asking a user to specify this function explicitly, which is unrealistic, we explicitly model the uncertainty in the utility function and propose a preference elicitation-based framework for learning the utility function through feedback provided by the user. We propose several sampling-based methods which, given user feedback, can capture the updated utility function. We develop an efficient algorithm for generating top- k packages using the learned utility function, where the rank ordering respects any of a variety of ranking semantics proposed in the literature. Through extensive experiments on both real and synthetic datasets, we demonstrate the efficiency and effectiveness of the proposed system for finding top- k packages.</abstract><doi>10.14778/2733085.2733099</doi><tpages>12</tpages><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier ISSN: 2150-8097
ispartof Proceedings of the VLDB Endowment, 2014-10, Vol.7 (14), p.1941-1952
issn 2150-8097
2150-8097
language eng
recordid cdi_crossref_primary_10_14778_2733085_2733099
source Association for Computing Machinery:Jisc Collections:ACM OPEN Journals 2023-2025 (reading list)
title Generating top-k packages via preference elicitation
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-14T01%3A47%3A19IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-crossref&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Generating%20top-k%20packages%20via%20preference%20elicitation&rft.jtitle=Proceedings%20of%20the%20VLDB%20Endowment&rft.au=Xie,%20Min&rft.date=2014-10&rft.volume=7&rft.issue=14&rft.spage=1941&rft.epage=1952&rft.pages=1941-1952&rft.issn=2150-8097&rft.eissn=2150-8097&rft_id=info:doi/10.14778/2733085.2733099&rft_dat=%3Ccrossref%3E10_14778_2733085_2733099%3C/crossref%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c285t-b3b5f833ddfede4b7a7bd1a1d3db10bf34d313b36827c0100a6cb01e026954e63%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true