{"id":"https://openalex.org/W2603439645","doi":"https://doi.org/10.5815/ijitcs.2017.03.06","title":"Data Cleaning In Data Warehouse: A Survey of Data Pre-processing Techniques and Tools","display_name":"Data Cleaning In Data Warehouse: A Survey of Data Pre-processing Techniques and Tools","publication_year":2017,"publication_date":"2017-03-08","ids":{"openalex":"https://openalex.org/W2603439645","doi":"https://doi.org/10.5815/ijitcs.2017.03.06","mag":"2603439645"},"language":"en","primary_location":{"id":"doi:10.5815/ijitcs.2017.03.06","doi":"https://doi.org/10.5815/ijitcs.2017.03.06","is_oa":true,"landing_page_url":"https://doi.org/10.5815/ijitcs.2017.03.06","pdf_url":"http://www.mecs-press.org/ijitcs/ijitcs-v9-n3/IJITCS-V9-N3-6.pdf","source":{"id":"https://openalex.org/S2483513740","display_name":"International Journal of Information Technology and Computer Science","issn_l":"2074-9007","issn":["2074-9007","2074-9015"],"is_oa":true,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Information Technology and Computer Science","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"http://www.mecs-press.org/ijitcs/ijitcs-v9-n3/IJITCS-V9-N3-6.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091357800","display_name":"Anosh Fatima","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I201384688","display_name":"National University of Computer and Emerging Sciences","ror":"https://ror.org/003eyb898","country_code":"PK","type":"education","lineage":["https://openalex.org/I201384688"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Anosh Fatima","raw_affiliation_strings":["National University of Computer and Emerging Sciences, Faisalabad, 38000, Pakistan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Computer and Emerging Sciences, Faisalabad, 38000, Pakistan","institution_ids":["https://openalex.org/I201384688"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5096308073","display_name":"Nosheen Nazir","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I201384688","display_name":"National University of Computer and Emerging Sciences","ror":"https://ror.org/003eyb898","country_code":"PK","type":"education","lineage":["https://openalex.org/I201384688"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Nosheen Nazir","raw_affiliation_strings":["National University of Computer and Emerging Sciences, Faisalabad, 38000, Pakistan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Computer and Emerging Sciences, Faisalabad, 38000, Pakistan","institution_ids":["https://openalex.org/I201384688"]}]},{"author_position":"last","author":{"id":null,"display_name":"Muhammad Gufran Khan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I201384688","display_name":"National University of Computer and Emerging Sciences","ror":"https://ror.org/003eyb898","country_code":"PK","type":"education","lineage":["https://openalex.org/I201384688"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Muhammad Gufran Khan","raw_affiliation_strings":["National University of Computer and Emerging Sciences, Faisalabad, 38000, Pakistan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Computer and Emerging Sciences, Faisalabad, 38000, Pakistan","institution_ids":["https://openalex.org/I201384688"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I201384688"],"apc_list":null,"apc_paid":null,"fwci":2.4165,"has_fulltext":true,"cited_by_count":37,"citation_normalized_percentile":{"value":0.89282672,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":99},"biblio":{"volume":"9","issue":"3","first_page":"50","last_page":"61"},"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/T11891","display_name":"Big Data and Business Intelligence","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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-cleaning","display_name":"data cleaning","score":0.9369999766349792},{"id":"https://openalex.org/keywords/data-preprocessing","display_name":"data preprocessing","score":0.828000009059906},{"id":"https://openalex.org/keywords/data-warehouse","display_name":"data warehouse","score":0.921999990940094},{"id":"https://openalex.org/keywords/data-quality","display_name":"data quality","score":0.9520000219345093},{"id":"https://openalex.org/keywords/yale-university","display_name":"Yale University","score":0.7269999980926514},{"id":"https://openalex.org/keywords/weka","display_name":"WEKA","score":0.7879999876022339},{"id":"https://openalex.org/keywords/data-standardization","display_name":"data standardization","score":0.7129999995231628},{"id":"https://openalex.org/keywords/data-matching","display_name":"data matching","score":0.8140000104904175},{"id":"https://openalex.org/keywords/data-transformation","display_name":"data transformation","score":0.8479999899864197},{"id":"https://openalex.org/keywords/data-audit","display_name":"data auditing","score":0.8349999785423279},{"id":"https://openalex.org/keywords/pattern-detection","display_name":"pattern detection","score":0.6330000162124634}],"concepts":[{"id":"https://openalex.org/C135572916","wikidata":"https://www.wikidata.org/wiki/Q193351","display_name":"Data warehouse","level":2,"score":0.9194697737693787},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8519851565361023},{"id":"https://openalex.org/C42199009","wikidata":"https://www.wikidata.org/wiki/Q1172378","display_name":"Data cleansing","level":4,"score":0.7053967118263245},{"id":"https://openalex.org/C150670458","wikidata":"https://www.wikidata.org/wiki/Q4272815","display_name":"Data transformation","level":3,"score":0.6431474089622498},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.6277698278427124},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.6257742643356323},{"id":"https://openalex.org/C191087605","wikidata":"https://www.wikidata.org/wiki/Q1501395","display_name":"Online transaction processing","level":4,"score":0.6121620535850525},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.5209059119224548},{"id":"https://openalex.org/C68387754","wikidata":"https://www.wikidata.org/wiki/Q7271585","display_name":"Schedule","level":2,"score":0.4940817654132843},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4542272090911865},{"id":"https://openalex.org/C127722929","wikidata":"https://www.wikidata.org/wiki/Q7833714","display_name":"Transaction data","level":3,"score":0.44779491424560547},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.42990753054618835},{"id":"https://openalex.org/C143008350","wikidata":"https://www.wikidata.org/wiki/Q3432172","display_name":"Dimensional modeling","level":2,"score":0.4283847212791443},{"id":"https://openalex.org/C2767350","wikidata":"https://www.wikidata.org/wiki/Q6662173","display_name":"Business intelligence","level":2,"score":0.420066773891449},{"id":"https://openalex.org/C201932085","wikidata":"https://www.wikidata.org/wiki/Q642514","display_name":"Online analytical processing","level":3,"score":0.4167739450931549},{"id":"https://openalex.org/C75949130","wikidata":"https://www.wikidata.org/wiki/Q848010","display_name":"Database transaction","level":2,"score":0.3875699043273926},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.35711199045181274},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"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/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5815/ijitcs.2017.03.06","doi":"https://doi.org/10.5815/ijitcs.2017.03.06","is_oa":true,"landing_page_url":"https://doi.org/10.5815/ijitcs.2017.03.06","pdf_url":"http://www.mecs-press.org/ijitcs/ijitcs-v9-n3/IJITCS-V9-N3-6.pdf","source":{"id":"https://openalex.org/S2483513740","display_name":"International Journal of Information Technology and Computer Science","issn_l":"2074-9007","issn":["2074-9007","2074-9015"],"is_oa":true,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Information Technology and Computer Science","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.5815/ijitcs.2017.03.06","doi":"https://doi.org/10.5815/ijitcs.2017.03.06","is_oa":true,"landing_page_url":"https://doi.org/10.5815/ijitcs.2017.03.06","pdf_url":"http://www.mecs-press.org/ijitcs/ijitcs-v9-n3/IJITCS-V9-N3-6.pdf","source":{"id":"https://openalex.org/S2483513740","display_name":"International Journal of Information Technology and Computer Science","issn_l":"2074-9007","issn":["2074-9007","2074-9015"],"is_oa":true,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Information Technology and Computer Science","raw_type":"journal-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"score":0.5099999904632568,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2603439645.pdf","grobid_xml":"https://content.openalex.org/works/W2603439645.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W161449699","https://openalex.org/W858668936","https://openalex.org/W1503556420","https://openalex.org/W1610496399","https://openalex.org/W1615274412","https://openalex.org/W1736726159","https://openalex.org/W2007318901","https://openalex.org/W2031031312","https://openalex.org/W2031250218","https://openalex.org/W2039781767","https://openalex.org/W2074489032","https://openalex.org/W2078501237","https://openalex.org/W2107743371","https://openalex.org/W2109574129","https://openalex.org/W2121989901","https://openalex.org/W2131666008","https://openalex.org/W2138993612","https://openalex.org/W2147219397","https://openalex.org/W2163930361","https://openalex.org/W2278402246","https://openalex.org/W2329195817","https://openalex.org/W2542372770","https://openalex.org/W2554064644","https://openalex.org/W2952451116","https://openalex.org/W4298096392","https://openalex.org/W6903887332","https://openalex.org/W6948989375"],"related_works":["https://openalex.org/W1541341370","https://openalex.org/W2109625514","https://openalex.org/W2349699607","https://openalex.org/W2061985295","https://openalex.org/W656573153","https://openalex.org/W2593811201","https://openalex.org/W197698241","https://openalex.org/W245400970","https://openalex.org/W2764054250","https://openalex.org/W4238407524"],"abstract_inverted_index":{"A":[0],"Data":[1,102],"Warehouse":[2,103],"is":[3,92,104],"a":[4,40],"computer":[5],"system":[6],"designed":[7],"for":[8,85,114,140],"storing":[9,69],"and":[10,28,43,48,79,121,135,150,179,187],"analyzing":[11],"an":[12,25],"organization's":[13],"historical":[14],"data":[15,37,71,76,115,127,146,148,155,185],"from":[16,31],"day-to-day":[17],"operations":[18],"in":[19,82,94,147,170,184,190],"Online":[20],"Transaction":[21],"Processing":[22],"System":[23],"(OLTP).Usually,":[24],"organization":[26],"summarizes":[27],"copies":[29],"information":[30,52],"its":[32],"operational":[33,57],"systems":[34],"to":[35,60,63,97,143],"the":[36,51,56,80,99,145,157,163,191],"warehouse":[38,149],"on":[39,50,123],"regular":[41],"schedule":[42],"management":[44],"performs":[45],"complex":[46],"queries":[47],"analysis":[49],"without":[53],"slowing":[54],"down":[55],"systems.Data":[58],"need":[59],"be":[61,168],"pre-processed":[62],"improve":[64,98],"quality":[65,129],"of":[66,90,101,107,126,162,165],"data,":[67],"before":[68],"into":[70],"warehouse.This":[72],"survey":[73],"paper":[74,166],"presents":[75],"cleaning":[77],"problems":[78],"approaches":[81],"use":[83],"currently":[84],"preprocessing.To":[86],"determine":[87],"which":[88],"technique":[89],"preprocessing":[91],"best":[93],"what":[95],"scenario":[96],"performance":[100],"main":[105],"goal":[106],"this":[108],"paper.Many":[109],"techniques":[110],"have":[111,137],"been":[112,138],"analyzed":[113],"cleansing,":[116,175],"using":[117],"certain":[118],"evaluation":[119],"attributes":[120],"tested":[122],"different":[124],"kind":[125],"sets.Data":[128],"tools":[130],"such":[131],"as":[132],"YALE,":[133],"ALTERYX,":[134],"WEKA":[136],"used":[139],"conclusive":[141],"results":[142],"ready":[144],"ensure":[151],"that":[152],"only":[153],"cleaned":[154],"populates":[156],"warehouse,":[158],"thus":[159],"enhancing":[160],"usability":[161],"warehouse.Results":[164],"can":[167,182],"useful":[169],"many":[171],"future":[172],"activities":[173],"like":[174],"standardizing,":[176],"correction,":[177],"matching":[178],"transformation.This":[180],"research":[181],"help":[183],"auditing":[186],"pattern":[188],"detection":[189],"data.":[192]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":2}],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2017-04-07T00:00:00"}
