{"id":"https://openalex.org/W1978271507","doi":"https://doi.org/10.1145/2792838.2799670","title":"Data Quality Matters in Recommender Systems","display_name":"Data Quality Matters in Recommender Systems","publication_year":2015,"publication_date":"2015-09-08","ids":{"openalex":"https://openalex.org/W1978271507","doi":"https://doi.org/10.1145/2792838.2799670","mag":"1978271507"},"language":"en","primary_location":{"id":"doi:10.1145/2792838.2799670","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2792838.2799670","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 9th ACM Conference on Recommender Systems","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5026428283","display_name":"Oren Sar Shalom","orcid":"https://orcid.org/0000-0002-5242-3932"},"institutions":[{"id":"https://openalex.org/I13955877","display_name":"Bar-Ilan University","ror":"https://ror.org/03kgsv495","country_code":"IL","type":"education","lineage":["https://openalex.org/I13955877"]},{"id":"https://openalex.org/I4210125051","display_name":"Microsoft (Israel)","ror":"https://ror.org/03819cc96","country_code":"IL","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210125051"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Oren Sar Shalom","raw_affiliation_strings":["Microsoft and Bar Ilan University, Herzliya, Israel","Microsoft and Bar Ilan University, Herzliya, Israel#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft and Bar Ilan University, Herzliya, Israel","institution_ids":["https://openalex.org/I4210125051","https://openalex.org/I13955877"]},{"raw_affiliation_string":"Microsoft and Bar Ilan University, Herzliya, Israel#TAB#","institution_ids":["https://openalex.org/I13955877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047191996","display_name":"Shlomo Berkovsky","orcid":"https://orcid.org/0000-0003-2638-4121"},"institutions":[{"id":"https://openalex.org/I1292875679","display_name":"Commonwealth Scientific and Industrial Research Organisation","ror":"https://ror.org/03qn8fb07","country_code":"AU","type":"government","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Shlomo Berkovsky","raw_affiliation_strings":["CSIRO, Marsfield, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CSIRO, Marsfield, Australia","institution_ids":["https://openalex.org/I1292875679"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033389618","display_name":"Royi Ronen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210125051","display_name":"Microsoft (Israel)","ror":"https://ror.org/03819cc96","country_code":"IL","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210125051"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Royi Ronen","raw_affiliation_strings":["Microsoft, Herzliya, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft, Herzliya, Israel","institution_ids":["https://openalex.org/I4210125051"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091747444","display_name":"Elad Ziklik","orcid":null},"institutions":[{"id":"https://openalex.org/I4210125051","display_name":"Microsoft (Israel)","ror":"https://ror.org/03819cc96","country_code":"IL","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210125051"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Elad Ziklik","raw_affiliation_strings":["Microsoft, Herzliya, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft, Herzliya, Israel","institution_ids":["https://openalex.org/I4210125051"]}]},{"author_position":"last","author":{"id":null,"display_name":"Amir Amihood","orcid":null},"institutions":[{"id":"https://openalex.org/I13955877","display_name":"Bar-Ilan University","ror":"https://ror.org/03kgsv495","country_code":"IL","type":"education","lineage":["https://openalex.org/I13955877"]},{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["IL","US"],"is_corresponding":false,"raw_author_name":"Amir Amihood","raw_affiliation_strings":["Bar Ilan University and Johns Hopkins University, Ramat Gan, Israel","Bar Ilan University and Johns Hopkins University, Ramat Gan, Israel#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bar Ilan University and Johns Hopkins University, Ramat Gan, Israel","institution_ids":["https://openalex.org/I145311948","https://openalex.org/I13955877"]},{"raw_affiliation_string":"Bar Ilan University and Johns Hopkins University, Ramat Gan, Israel#TAB#","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.0584,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.87770317,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"257","last_page":"260"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9954000115394592,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9948999881744385,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/data-cleansing","display_name":"Data cleansing","score":0.8902339339256287},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8478090763092041},{"id":"https://openalex.org/keywords/recommender-system","display_name":"Recommender system","score":0.796368420124054},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.6186710596084595},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.6031408905982971},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5901124477386475},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4840964078903198},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.44229254126548767},{"id":"https://openalex.org/keywords/data-collection","display_name":"Data collection","score":0.4357430338859558},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3538162112236023},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.1799921989440918},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.07438886165618896}],"concepts":[{"id":"https://openalex.org/C42199009","wikidata":"https://www.wikidata.org/wiki/Q1172378","display_name":"Data cleansing","level":4,"score":0.8902339339256287},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8478090763092041},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.796368420124054},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.6186710596084595},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.6031408905982971},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5901124477386475},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4840964078903198},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.44229254126548767},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.4357430338859558},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3538162112236023},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.1799921989440918},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07438886165618896},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2792838.2799670","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2792838.2799670","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 9th ACM Conference on Recommender Systems","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1556081409","https://openalex.org/W1567491469","https://openalex.org/W1975825542","https://openalex.org/W2020631728","https://openalex.org/W2047870744","https://openalex.org/W2071937578","https://openalex.org/W2108630796","https://openalex.org/W2111275322","https://openalex.org/W2117366235","https://openalex.org/W2148943147"],"related_works":["https://openalex.org/W962911587","https://openalex.org/W4200551113","https://openalex.org/W2270762093","https://openalex.org/W2028861106","https://openalex.org/W4255072332","https://openalex.org/W3126834064","https://openalex.org/W3110671107","https://openalex.org/W1754154538","https://openalex.org/W3169246587","https://openalex.org/W4253714063"],"abstract_inverted_index":{"Although":[0],"data":[1,61,71,108],"quality":[2,25,72],"has":[3,17],"been":[4],"recognized":[5],"as":[6],"an":[7],"important":[8],"factor":[9],"in":[10,21,30,74],"the":[11,43,46,49,60,104,116,119],"broad":[12],"information":[13],"systems":[14],"research,":[15],"it":[16],"received":[18],"little":[19],"attention":[20],"recommender":[22,75],"systems.":[23],"Data":[24],"matters":[26],"are":[27],"typically":[28],"addressed":[29],"recommenders":[31],"by":[32],"ad-hoc":[33],"cleansing":[34,50,109],"methods,":[35],"which":[36],"prune":[37],"noisy":[38],"or":[39],"unreliable":[40],"records":[41],"from":[42],"data.":[44],"However,":[45],"setting":[47,84],"of":[48,59,96,118],"parameters":[51],"is":[52],"often":[53],"done":[54],"arbitrarily,":[55],"without":[56],"thorough":[57],"consideration":[58],"characteristics.":[62],"In":[63],"this":[64],"work,":[65],"we":[66],"turn":[67],"to":[68],"two":[69],"central":[70],"problems":[73],"systems:":[76],"sparsity":[77],"and":[78,87,90,98],"redundancy.":[79],"We":[80,101],"devise":[81],"models":[82,105],"for":[83],"data-dependent":[85],"thresholds":[86],"sampling":[88],"levels,":[89],"evaluate":[91],"these":[92],"using":[93],"a":[94],"collection":[95],"public":[97],"proprietary":[99],"datasets.":[100],"observe":[102],"that":[103],"accurately":[106],"predict":[107],"parameters,":[110],"while":[111],"having":[112],"minor":[113],"effect":[114],"on":[115],"accuracy":[117],"generated":[120],"recommendations.":[121]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}