{"id":"https://openalex.org/W3008739634","doi":"https://doi.org/10.1109/bigdata47090.2019.9006187","title":"DQA: Scalable, Automated and Interactive Data Quality Advisor","display_name":"DQA: Scalable, Automated and Interactive Data Quality Advisor","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W3008739634","doi":"https://doi.org/10.1109/bigdata47090.2019.9006187","mag":"3008739634"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata47090.2019.9006187","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata47090.2019.9006187","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5044958272","display_name":"Shrey Shrivastava","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shrey Shrivastava","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Kitchawan Rd, Yorktown Heights, NY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Kitchawan Rd, Yorktown Heights, NY","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033934770","display_name":"Dhaval Patel","orcid":"https://orcid.org/0000-0001-6210-0902"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dhaval Patel","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Kitchawan Rd, Yorktown Heights, NY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Kitchawan Rd, Yorktown Heights, NY","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039999123","display_name":"Anuradha Bhamidipaty","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anuradha Bhamidipaty","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Kitchawan Rd, Yorktown Heights, NY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Kitchawan Rd, Yorktown Heights, NY","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064019498","display_name":"Wesley M. Gifford","orcid":"https://orcid.org/0000-0003-3678-8410"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wesley M. Gifford","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Kitchawan Rd, Yorktown Heights, NY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Kitchawan Rd, Yorktown Heights, NY","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059334687","display_name":"Stuart Siegel","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stuart A. Siegel","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Kitchawan Rd, Yorktown Heights, NY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Kitchawan Rd, Yorktown Heights, NY","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041549091","display_name":"Venkata Sitaramagiridharganesh Ganapavarapu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Venkata Sitaramagiridharganesh Ganapavarapu","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Kitchawan Rd, Yorktown Heights, NY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Kitchawan Rd, Yorktown Heights, NY","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057936833","display_name":"Jayant Kalagnanam","orcid":"https://orcid.org/0009-0009-5051-2606"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jayant R. Kalagnanam","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Kitchawan Rd, Yorktown Heights, NY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Kitchawan Rd, Yorktown Heights, NY","institution_ids":["https://openalex.org/I4210114115"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210114115"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"2019","issue":null,"first_page":"2913","last_page":"2922"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9994999766349792,"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":0.9994999766349792,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.996399998664856,"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":0.9939000010490417,"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/computer-science","display_name":"Computer science","score":0.8236469030380249},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7012263536453247},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5063623189926147},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.44835197925567627},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.36728402972221375},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06840837001800537}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8236469030380249},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7012263536453247},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5063623189926147},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.44835197925567627},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.36728402972221375},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06840837001800537},{"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/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"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":2,"locations":[{"id":"doi:10.1109/bigdata47090.2019.9006187","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata47090.2019.9006187","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},{"id":"mag:3087630297","is_oa":false,"landing_page_url":"https://jglobal.jst.go.jp/en/detail?JGLOBAL_ID=202002265439040757","pdf_url":null,"source":{"id":"https://openalex.org/S4306512817","display_name":"IEEE Conference Proceedings","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":"IEEE Conference Proceedings","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.6200000047683716}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W2182361439","https://openalex.org/W2437617937","https://openalex.org/W2437990191","https://openalex.org/W2805655759","https://openalex.org/W2889249015","https://openalex.org/W2898162267","https://openalex.org/W2946016581","https://openalex.org/W2946595616","https://openalex.org/W2948950196","https://openalex.org/W3133714496","https://openalex.org/W4285719527","https://openalex.org/W6685961532"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2389214306","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W4391913857","https://openalex.org/W2350741829"],"abstract_inverted_index":{"Fueled":[0],"with":[1],"growth":[2],"in":[3,23,65,113,195],"the":[4,19,66,73,98,108,125,146,201],"fields":[5],"of":[6,8,18,45,75,104,110,148,154,190],"Internet":[7],"Things":[9],"(IoT)":[10],"and":[11,39,47,77,88,107,170,199],"Big":[12],"Data,":[13],"data":[14,31,53,58,69,79,90,115,126,137,176,182],"has":[15],"become":[16],"one":[17],"most":[20],"valuable":[21],"assets":[22],"today's":[24],"world.":[25],"While":[26],"we":[27,82,96,185],"are":[28],"leveraging":[29],"this":[30,94],"for":[32,123,135,140,181],"analyzing":[33],"complex":[34],"systems":[35],"using":[36],"machine":[37],"learning":[38],"deep":[40],"learning,":[41],"a":[42,85,114,120,141,152,178,187,196],"considerable":[43],"amount":[44],"time":[46],"effort":[48,74],"is":[49,193],"spent":[50],"on":[51],"addressing":[52,78],"quality":[54,59,80,91,127],"issues.":[55],"If":[56],"undetected,":[57],"issues":[60,172],"can":[61],"cause":[62],"large":[63],"deviations":[64],"analysis,":[67],"misleading":[68],"scientists.":[70,183],"To":[71],"ease":[72],"identifying":[76],"challenges,":[81],"introduce":[83],"DQA,":[84],"scalable,":[86],"automated":[87],"interactive":[89],"advisor.":[92],"In":[93],"paper,":[95],"describe":[97,200],"DQA":[99,149,166,192],"framework,":[100],"provide":[101,162,186],"detailed":[102],"description":[103],"its":[105],"components":[106],"benefits":[109,202],"integrating":[111],"it":[112],"science":[116],"process.":[117],"We":[118,144,161],"propose":[119],"programmatic":[121],"approach":[122],"implementing":[124],"framework":[128],"which":[129,173],"automatically":[130],"generates":[131],"dynamic":[132],"executable":[133],"graphs":[134],"performing":[136],"validations":[138],"fine-tuned":[139],"given":[142],"dataset.":[143],"discuss":[145],"use":[147],"to":[150,158],"build":[151],"library":[153],"validation":[155],"checks":[156],"common":[157],"many":[159,168],"applications.":[160],"insight":[163],"into":[164],"how":[165,191],"addresses":[167],"persistence":[169],"usability":[171],"currently":[174],"make":[175],"cleaning":[177],"laborious":[179],"task":[180],"Finally,":[184],"case":[188],"study":[189],"implemented":[194],"realworld":[197],"system":[198],"realized.":[203]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}