{"id":"https://openalex.org/W3126450572","doi":"https://doi.org/10.4018/ijdwm.2021010105","title":"Enhancing Data Quality at ETL Stage of Data Warehousing","display_name":"Enhancing Data Quality at ETL Stage of Data Warehousing","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3126450572","doi":"https://doi.org/10.4018/ijdwm.2021010105","mag":"3126450572"},"language":"en","primary_location":{"id":"doi:10.4018/ijdwm.2021010105","is_oa":false,"landing_page_url":"https://doi.org/10.4018/ijdwm.2021010105","pdf_url":null,"source":{"id":"https://openalex.org/S53932126","display_name":"International Journal of Data Warehousing and Mining","issn_l":"1548-3924","issn":["1548-3924","1548-3932"],"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 Data Warehousing and Mining","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/A5100605662","display_name":"Neha Gupta","orcid":"https://orcid.org/0000-0003-0905-5457"},"institutions":[{"id":"https://openalex.org/I55016150","display_name":"Manav Rachna International Institute of Research and Studies","ror":"https://ror.org/02kf4r633","country_code":"IN","type":"education","lineage":["https://openalex.org/I4405253735","https://openalex.org/I55016150"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Neha Gupta","raw_affiliation_strings":["Manav Rachna International Institute of Research and Studies, Faridabad, India"],"raw_orcid":"https://orcid.org/0000-0003-0905-5457","affiliations":[{"raw_affiliation_string":"Manav Rachna International Institute of Research and Studies, Faridabad, India","institution_ids":["https://openalex.org/I55016150"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066305365","display_name":"Sakshi Jolly","orcid":null},"institutions":[{"id":"https://openalex.org/I55016150","display_name":"Manav Rachna International Institute of Research and Studies","ror":"https://ror.org/02kf4r633","country_code":"IN","type":"education","lineage":["https://openalex.org/I4405253735","https://openalex.org/I55016150"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sakshi Jolly","raw_affiliation_strings":["Manav Rachna International Institute of Research and Studies, Faridabad, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Manav Rachna International Institute of Research and Studies, Faridabad, India","institution_ids":["https://openalex.org/I55016150"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100605662"],"corresponding_institution_ids":["https://openalex.org/I55016150"],"apc_list":null,"apc_paid":null,"fwci":0.5375,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.75083451,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":"17","issue":"1","first_page":"74","last_page":"91"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11396","display_name":"Artificial Intelligence in Healthcare","score":0.9969000220298767,"subfield":{"id":"https://openalex.org/subfields/3605","display_name":"Health Information Management"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T11396","display_name":"Artificial Intelligence in Healthcare","score":0.9969000220298767,"subfield":{"id":"https://openalex.org/subfields/3605","display_name":"Health Information Management"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11891","display_name":"Big Data and Business Intelligence","score":0.9955999851226807,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9955000281333923,"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":0.8404593467712402},{"id":"https://openalex.org/keywords/data-warehouse","display_name":"Data warehouse","score":0.8292234539985657},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6947079300880432},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.6013912558555603},{"id":"https://openalex.org/keywords/missing-data","display_name":"Missing data","score":0.4894041121006012},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.46271181106567383},{"id":"https://openalex.org/keywords/data-transformation","display_name":"Data transformation","score":0.44626468420028687},{"id":"https://openalex.org/keywords/data-cleansing","display_name":"Data cleansing","score":0.4449281692504883},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.41980475187301636},{"id":"https://openalex.org/keywords/euclidean-distance","display_name":"Euclidean distance","score":0.4183763861656189},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.32678818702697754},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.11084076762199402},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.0963815450668335}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8404593467712402},{"id":"https://openalex.org/C135572916","wikidata":"https://www.wikidata.org/wiki/Q193351","display_name":"Data warehouse","level":2,"score":0.8292234539985657},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6947079300880432},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.6013912558555603},{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.4894041121006012},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.46271181106567383},{"id":"https://openalex.org/C150670458","wikidata":"https://www.wikidata.org/wiki/Q4272815","display_name":"Data transformation","level":3,"score":0.44626468420028687},{"id":"https://openalex.org/C42199009","wikidata":"https://www.wikidata.org/wiki/Q1172378","display_name":"Data cleansing","level":4,"score":0.4449281692504883},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.41980475187301636},{"id":"https://openalex.org/C120174047","wikidata":"https://www.wikidata.org/wiki/Q847073","display_name":"Euclidean distance","level":2,"score":0.4183763861656189},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.32678818702697754},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.11084076762199402},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.0963815450668335},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.4018/ijdwm.2021010105","is_oa":false,"landing_page_url":"https://doi.org/10.4018/ijdwm.2021010105","pdf_url":null,"source":{"id":"https://openalex.org/S53932126","display_name":"International Journal of Data Warehousing and Mining","issn_l":"1548-3924","issn":["1548-3924","1548-3932"],"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 Data Warehousing and Mining","raw_type":"journal-article"},{"id":"pmh:oai:RePEc:igg:jdwm00:v:17:y:2021:i:1:p:74-91","is_oa":false,"landing_page_url":"https://services.igi-global.com/resolvedoi/resolve.aspx?doi=10.4018/IJDWM.2021010105","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1997437882","https://openalex.org/W2094995356","https://openalex.org/W2164424382","https://openalex.org/W2195118355","https://openalex.org/W2306386573","https://openalex.org/W2548753368","https://openalex.org/W2559185041","https://openalex.org/W2595582532","https://openalex.org/W2603439645","https://openalex.org/W2603580523","https://openalex.org/W2606702010","https://openalex.org/W2610135452","https://openalex.org/W2770848963","https://openalex.org/W2773910439","https://openalex.org/W2792572948","https://openalex.org/W2792920932","https://openalex.org/W2794656727","https://openalex.org/W2795539379","https://openalex.org/W2801351100","https://openalex.org/W2801584337","https://openalex.org/W2889199656","https://openalex.org/W2910711941","https://openalex.org/W2912274100","https://openalex.org/W2921597415","https://openalex.org/W2945368864"],"related_works":["https://openalex.org/W2353590449","https://openalex.org/W1542560311","https://openalex.org/W2159392828","https://openalex.org/W2335291181","https://openalex.org/W2003588249","https://openalex.org/W2735063176","https://openalex.org/W69955301","https://openalex.org/W2181836431","https://openalex.org/W2181930696","https://openalex.org/W2353586736"],"abstract_inverted_index":{"Data":[0,47],"usually":[1],"comes":[2],"into":[3,16,159],"data":[4,25,36,44,52,65,68,125,147,155,161],"warehouses":[5],"from":[6],"multiple":[7],"sources":[8],"having":[9],"different":[10],"formats":[11],"and":[12,22,33,62,73,126,149],"are":[13,28],"specifically":[14],"categorized":[15],"three":[17],"groups":[18],"(i.e.,":[19],"structured,":[20],"semi-structured,":[21],"unstructured).":[23],"Various":[24],"mining":[26],"technologies":[27],"used":[29],"to":[30,40,55,60,101,110,119,134,156],"collect,":[31],"refine,":[32],"analyze":[34],"the":[35,41,51,64,95,121,146],"which":[37,78],"further":[38],"leads":[39],"problem":[42],"of":[43,123],"quality":[45,148],"management.":[46],"purgation":[48],"occurs":[49],"when":[50],"is":[53],"subject":[54],"ETL":[56],"methodology":[57],"in":[58,138,152],"order":[59],"maintain":[61],"improve":[63,120],"quality.":[66],"The":[67,90],"may":[69,74],"contain":[70],"unnecessary":[71],"information":[72],"have":[75,144],"inappropriate":[76],"symbols":[77],"can":[79],"be":[80,157],"defined":[81],"as":[82],"dummy":[83,112],"values,":[84,86,113],"cryptic":[85,103],"or":[87],"missing":[88,136],"values.":[89],"present":[91],"work":[92],"has":[93],"improved":[94,145],"expectation-maximization":[96],"algorithm":[97,115,128],"with":[98,107,116,130],"dot":[99],"product":[100],"handle":[102,135],"data,":[104],"DBSCAN":[105],"method":[106],"Gower":[108],"metrics":[109,133,143],"ensure":[111],"Wards":[114],"Minkowski":[117],"distance":[118,132,142],"results":[122],"contradicting":[124],"K-means":[127],"along":[129],"Euclidean":[131],"values":[137],"a":[139,160],"dataset.":[140],"These":[141],"also":[150],"helped":[151],"providing":[153],"consistent":[154],"loaded":[158],"warehouse.":[162]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}