{"id":"https://openalex.org/W2095086096","doi":"https://doi.org/10.4018/ijkbo.2011100104","title":"An Efficient Algorithm for Data Cleaning","display_name":"An Efficient Algorithm for Data Cleaning","publication_year":2011,"publication_date":"2011-10-01","ids":{"openalex":"https://openalex.org/W2095086096","doi":"https://doi.org/10.4018/ijkbo.2011100104","mag":"2095086096"},"language":"en","primary_location":{"id":"doi:10.4018/ijkbo.2011100104","is_oa":false,"landing_page_url":"https://doi.org/10.4018/ijkbo.2011100104","pdf_url":null,"source":{"id":"https://openalex.org/S4210171617","display_name":"International Journal of Knowledge-Based Organizations","issn_l":"2155-6393","issn":["2155-6393","2155-6407"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320424","host_organization_name":"IGI Global","host_organization_lineage":["https://openalex.org/P4310320424"],"host_organization_lineage_names":["IGI Global"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Knowledge-Based Organizations","raw_type":"journal-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/A5114249366","display_name":"Payal Pahwa","orcid":null},"institutions":[{"id":"https://openalex.org/I105454292","display_name":"Guru Gobind Singh Indraprastha University","ror":"https://ror.org/034q1za58","country_code":"IN","type":"education","lineage":["https://openalex.org/I105454292"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Payal Pahwa","raw_affiliation_strings":["Guru Gobind Singh IndraPrastha University, India","[Guru Gobind Singh Indraprastha University, India]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guru Gobind Singh IndraPrastha University, India","institution_ids":["https://openalex.org/I105454292"]},{"raw_affiliation_string":"[Guru Gobind Singh Indraprastha University, India]","institution_ids":["https://openalex.org/I105454292"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088520267","display_name":"Rajiv Arora","orcid":null},"institutions":[{"id":"https://openalex.org/I105454292","display_name":"Guru Gobind Singh Indraprastha University","ror":"https://ror.org/034q1za58","country_code":"IN","type":"education","lineage":["https://openalex.org/I105454292"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Rajiv Arora","raw_affiliation_strings":["Guru Gobind Singh IndraPrastha University, India","[Guru Gobind Singh Indraprastha University, India]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guru Gobind Singh IndraPrastha University, India","institution_ids":["https://openalex.org/I105454292"]},{"raw_affiliation_string":"[Guru Gobind Singh Indraprastha University, India]","institution_ids":["https://openalex.org/I105454292"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005684143","display_name":"Garima Thakur","orcid":"https://orcid.org/0000-0003-0684-7643"},"institutions":[{"id":"https://openalex.org/I105454292","display_name":"Guru Gobind Singh Indraprastha University","ror":"https://ror.org/034q1za58","country_code":"IN","type":"education","lineage":["https://openalex.org/I105454292"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Garima Thakur","raw_affiliation_strings":["Guru Gobind Singh IndraPrastha University, India","[Guru Gobind Singh Indraprastha University, India]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guru Gobind Singh IndraPrastha University, India","institution_ids":["https://openalex.org/I105454292"]},{"raw_affiliation_string":"[Guru Gobind Singh Indraprastha University, India]","institution_ids":["https://openalex.org/I105454292"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I105454292"],"apc_list":null,"apc_paid":null,"fwci":1.2508,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.82203652,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"1","issue":"4","first_page":"56","last_page":"71"},"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9904000163078308,"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"}},{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.989799976348877,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/data-warehouse","display_name":"Data warehouse","score":0.7745419144630432},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7093072533607483},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.7075746059417725},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.6801954507827759},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6011353731155396},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5471346974372864},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.4894813299179077},{"id":"https://openalex.org/keywords/data-cleansing","display_name":"Data cleansing","score":0.47949057817459106},{"id":"https://openalex.org/keywords/data-source","display_name":"Data source","score":0.46426889300346375},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.4246899485588074},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.41892534494400024},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3792319893836975},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12756004929542542},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.10197743773460388},{"id":"https://openalex.org/keywords/operations-management","display_name":"Operations management","score":0.07907214760780334}],"concepts":[{"id":"https://openalex.org/C135572916","wikidata":"https://www.wikidata.org/wiki/Q193351","display_name":"Data warehouse","level":2,"score":0.7745419144630432},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7093072533607483},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.7075746059417725},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.6801954507827759},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6011353731155396},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5471346974372864},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.4894813299179077},{"id":"https://openalex.org/C42199009","wikidata":"https://www.wikidata.org/wiki/Q1172378","display_name":"Data cleansing","level":4,"score":0.47949057817459106},{"id":"https://openalex.org/C2983685735","wikidata":"https://www.wikidata.org/wiki/Q5227355","display_name":"Data source","level":2,"score":0.46426889300346375},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4246899485588074},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.41892534494400024},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3792319893836975},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12756004929542542},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.10197743773460388},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.07907214760780334},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","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":2,"locations":[{"id":"doi:10.4018/ijkbo.2011100104","is_oa":false,"landing_page_url":"https://doi.org/10.4018/ijkbo.2011100104","pdf_url":null,"source":{"id":"https://openalex.org/S4210171617","display_name":"International Journal of Knowledge-Based Organizations","issn_l":"2155-6393","issn":["2155-6393","2155-6407"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320424","host_organization_name":"IGI Global","host_organization_lineage":["https://openalex.org/P4310320424"],"host_organization_lineage_names":["IGI Global"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Knowledge-Based Organizations","raw_type":"journal-article"},{"id":"pmh:oai:RePEc:igg:jkbo00:v:1:y:2011:i:4:p:56-71","is_oa":false,"landing_page_url":"http://services.igi-global.com/resolvedoi/resolve.aspx?doi=10.4018/ijkbo.2011100104","pdf_url":null,"source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.49000000953674316,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W574355879","https://openalex.org/W1484727516","https://openalex.org/W1513543741","https://openalex.org/W1550700900","https://openalex.org/W1612155886","https://openalex.org/W1976384389","https://openalex.org/W2024770506","https://openalex.org/W2068376489","https://openalex.org/W2072764742","https://openalex.org/W2089634871","https://openalex.org/W2106895292","https://openalex.org/W2128322880","https://openalex.org/W2131576956","https://openalex.org/W2141245797","https://openalex.org/W2165160451","https://openalex.org/W2271690868","https://openalex.org/W2753439427","https://openalex.org/W4254788633","https://openalex.org/W4301136025"],"related_works":["https://openalex.org/W2135633991","https://openalex.org/W962911587","https://openalex.org/W2270762093","https://openalex.org/W3126834064","https://openalex.org/W2353590449","https://openalex.org/W2353586736","https://openalex.org/W2735063176","https://openalex.org/W2181930696","https://openalex.org/W69955301","https://openalex.org/W2593811201"],"abstract_inverted_index":{"The":[0,59],"quality":[1,98],"of":[2,18,27,61,71,78,90,108],"real":[3],"world":[4],"data":[5,12,22,32,35,65,97],"that":[6,102,124],"is":[7,14,111,122,125],"being":[8],"fed":[9],"into":[10],"a":[11,15,25,119],"warehouse":[13],"major":[16,116],"concern":[17],"today.":[19],"As":[20],"the":[21,31,34,56,69,75,129],"comes":[23],"from":[24],"variety":[26],"sources":[28],"before":[29],"loading":[30],"in":[33,55],"warehouse,":[36],"it":[37,95],"must":[38],"be":[39,47],"checked":[40],"for":[41],"errors":[42],"and":[43,88,99],"anomalies.":[44],"There":[45],"may":[46],"exact":[48],"duplicate":[49,53,92],"records":[50,54],"or":[51,63],"approximate":[52],"source":[57],"data.":[58],"presence":[60],"incorrect":[62],"inconsistent":[64],"can":[66],"significantly":[67],"distort":[68],"results":[70],"analyses,":[72],"often":[73],"negating":[74],"potential":[76],"benefits":[77],"information-driven":[79],"approaches.":[80],"This":[81],"paper":[82],"addresses":[83],"issues":[84],"related":[85],"to":[86],"detection":[87],"correction":[89],"such":[91],"records.":[93],"Also,":[94],"analyzes":[96],"various":[100],"factors":[101],"degrade":[103],"it.":[104],"A":[105],"brief":[106],"analysis":[107],"existing":[109,130],"work":[110],"discussed,":[112],"pointing":[113],"out":[114],"its":[115],"limitations.":[117],"Thus,":[118],"new":[120],"framework":[121],"proposed":[123],"an":[126],"improvement":[127],"over":[128],"technique.":[131]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":2}],"updated_date":"2026-06-11T06:19:23.411458","created_date":"2025-10-10T00:00:00"}
