{"id":"https://openalex.org/W4399513333","doi":"https://doi.org/10.1007/s10515-024-00453-w","title":"Data cleaning and machine learning: a systematic literature review","display_name":"Data cleaning and machine learning: a systematic literature review","publication_year":2024,"publication_date":"2024-06-11","ids":{"openalex":"https://openalex.org/W4399513333","doi":"https://doi.org/10.1007/s10515-024-00453-w"},"language":"en","primary_location":{"id":"doi:10.1007/s10515-024-00453-w","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10515-024-00453-w","pdf_url":null,"source":{"id":"https://openalex.org/S4210177399","display_name":"Automated Software Engineering","issn_l":"0928-8910","issn":["0928-8910","1573-7535"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Automated Software Engineering","raw_type":"journal-article"},"type":"review","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/A5010998960","display_name":"Pierre-Olivier C\u00f4t\u00e9","orcid":"https://orcid.org/0009-0009-9937-1509"},"institutions":[{"id":"https://openalex.org/I45683168","display_name":"Polytechnique Montr\u00e9al","ror":"https://ror.org/05f8d4e86","country_code":"CA","type":"education","lineage":["https://openalex.org/I45683168"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Pierre-Olivier C\u00f4t\u00e9","raw_affiliation_strings":["Polytechnique Montr\u00e9al, Qu\u00e9bec, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Polytechnique Montr\u00e9al, Qu\u00e9bec, Canada","institution_ids":["https://openalex.org/I45683168"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079607563","display_name":"Amin Nikanjam","orcid":"https://orcid.org/0000-0002-0440-6839"},"institutions":[{"id":"https://openalex.org/I45683168","display_name":"Polytechnique Montr\u00e9al","ror":"https://ror.org/05f8d4e86","country_code":"CA","type":"education","lineage":["https://openalex.org/I45683168"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Amin Nikanjam","raw_affiliation_strings":["Polytechnique Montr\u00e9al, Qu\u00e9bec, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Polytechnique Montr\u00e9al, Qu\u00e9bec, Canada","institution_ids":["https://openalex.org/I45683168"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017346485","display_name":"Nafisa Ahmed","orcid":"https://orcid.org/0000-0001-9404-6410"},"institutions":[{"id":"https://openalex.org/I45683168","display_name":"Polytechnique Montr\u00e9al","ror":"https://ror.org/05f8d4e86","country_code":"CA","type":"education","lineage":["https://openalex.org/I45683168"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Nafisa Ahmed","raw_affiliation_strings":["Polytechnique Montr\u00e9al, Qu\u00e9bec, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Polytechnique Montr\u00e9al, Qu\u00e9bec, Canada","institution_ids":["https://openalex.org/I45683168"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041261532","display_name":"Dmytro Humeniuk","orcid":"https://orcid.org/0000-0002-2983-8312"},"institutions":[{"id":"https://openalex.org/I45683168","display_name":"Polytechnique Montr\u00e9al","ror":"https://ror.org/05f8d4e86","country_code":"CA","type":"education","lineage":["https://openalex.org/I45683168"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Dmytro Humeniuk","raw_affiliation_strings":["Polytechnique Montr\u00e9al, Qu\u00e9bec, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Polytechnique Montr\u00e9al, Qu\u00e9bec, Canada","institution_ids":["https://openalex.org/I45683168"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071052367","display_name":"Foutse Khomh","orcid":"https://orcid.org/0000-0002-5704-4173"},"institutions":[{"id":"https://openalex.org/I45683168","display_name":"Polytechnique Montr\u00e9al","ror":"https://ror.org/05f8d4e86","country_code":"CA","type":"education","lineage":["https://openalex.org/I45683168"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Foutse Khomh","raw_affiliation_strings":["Polytechnique Montr\u00e9al, Qu\u00e9bec, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Polytechnique Montr\u00e9al, Qu\u00e9bec, Canada","institution_ids":["https://openalex.org/I45683168"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5010998960"],"corresponding_institution_ids":["https://openalex.org/I45683168"],"apc_list":{"value":2290,"currency":"EUR","value_usd":2890},"apc_paid":null,"fwci":15.2984,"has_fulltext":false,"cited_by_count":84,"citation_normalized_percentile":{"value":0.9962963,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"31","issue":"2","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9975000023841858,"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":0.9975000023841858,"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":0.9937999844551086,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9476000070571899,"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/computer-science","display_name":"Computer science","score":0.6829923987388611},{"id":"https://openalex.org/keywords/systematic-review","display_name":"Systematic review","score":0.5632031559944153},{"id":"https://openalex.org/keywords/data-extraction","display_name":"Data extraction","score":0.5114632844924927},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.4930402934551239},{"id":"https://openalex.org/keywords/outlier","display_name":"Outlier","score":0.4733422100543976},{"id":"https://openalex.org/keywords/imputation","display_name":"Imputation (statistics)","score":0.4672033190727234},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.44347143173217773},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.415330708026886},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38722455501556396},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3497201204299927},{"id":"https://openalex.org/keywords/missing-data","display_name":"Missing data","score":0.25338834524154663},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1540060043334961},{"id":"https://openalex.org/keywords/medline","display_name":"MEDLINE","score":0.0959160327911377}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6829923987388611},{"id":"https://openalex.org/C189708586","wikidata":"https://www.wikidata.org/wiki/Q1504425","display_name":"Systematic review","level":3,"score":0.5632031559944153},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.5114632844924927},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.4930402934551239},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.4733422100543976},{"id":"https://openalex.org/C58041806","wikidata":"https://www.wikidata.org/wiki/Q1660484","display_name":"Imputation (statistics)","level":3,"score":0.4672033190727234},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.44347143173217773},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.415330708026886},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38722455501556396},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3497201204299927},{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.25338834524154663},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1540060043334961},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.0959160327911377},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","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/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s10515-024-00453-w","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10515-024-00453-w","pdf_url":null,"source":{"id":"https://openalex.org/S4210177399","display_name":"Automated Software Engineering","issn_l":"0928-8910","issn":["0928-8910","1573-7535"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Automated Software Engineering","raw_type":"journal-article"},{"id":"pmh:oai:publications.polymtl.ca:58621","is_oa":false,"landing_page_url":"https://publications.polymtl.ca/58621/","pdf_url":null,"source":{"id":"https://openalex.org/S4306401013","display_name":"PolyPublie (\u00c9cole Polytechnique de Montr\u00e9al)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I45683168","host_organization_name":"Polytechnique Montr\u00e9al","host_organization_lineage":["https://openalex.org/I45683168"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Article de revue"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309949","display_name":"Canadian Institute for Advanced Research","ror":"https://ror.org/01sdtdd95"},{"id":"https://openalex.org/F4320331165","display_name":"Fonds de recherche du Qu\u00e9bec","ror":"https://ror.org/00w3qhf76"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":193,"referenced_works":["https://openalex.org/W199035648","https://openalex.org/W1528361845","https://openalex.org/W1598553907","https://openalex.org/W1833314573","https://openalex.org/W1969456163","https://openalex.org/W1975675278","https://openalex.org/W2012611887","https://openalex.org/W2028644426","https://openalex.org/W2046372172","https://openalex.org/W2049058890","https://openalex.org/W2064675550","https://openalex.org/W2108598243","https://openalex.org/W2109646585","https://openalex.org/W2114363693","https://openalex.org/W2117079761","https://openalex.org/W2117539524","https://openalex.org/W2122777273","https://openalex.org/W2147717514","https://openalex.org/W2152498377","https://openalex.org/W2158933803","https://openalex.org/W2164187405","https://openalex.org/W2176159905","https://openalex.org/W2189149359","https://openalex.org/W2212902057","https://openalex.org/W2250539671","https://openalex.org/W2296719434","https://openalex.org/W2343875716","https://openalex.org/W2406470551","https://openalex.org/W2437617937","https://openalex.org/W2478432301","https://openalex.org/W2493916176","https://openalex.org/W2508179673","https://openalex.org/W2531327146","https://openalex.org/W2544062944","https://openalex.org/W2544486974","https://openalex.org/W2548122763","https://openalex.org/W2577784528","https://openalex.org/W2581973374","https://openalex.org/W2591700809","https://openalex.org/W2600366513","https://openalex.org/W2604861547","https://openalex.org/W2607643809","https://openalex.org/W2618530766","https://openalex.org/W2735825272","https://openalex.org/W2739643355","https://openalex.org/W2760451156","https://openalex.org/W2767681556","https://openalex.org/W2784560833","https://openalex.org/W2798649495","https://openalex.org/W2803237185","https://openalex.org/W2803913555","https://openalex.org/W2804269561","https://openalex.org/W2810591130","https://openalex.org/W2875652255","https://openalex.org/W2891177506","https://openalex.org/W2892341857","https://openalex.org/W2898576688","https://openalex.org/W2908058835","https://openalex.org/W2911749163","https://openalex.org/W2914436728","https://openalex.org/W2914585587","https://openalex.org/W2929493373","https://openalex.org/W2929941791","https://openalex.org/W2932881901","https://openalex.org/W2946504770","https://openalex.org/W2948145720","https://openalex.org/W2949679216","https://openalex.org/W2949736877","https://openalex.org/W2951147191","https://openalex.org/W2962762068","https://openalex.org/W2962802452","https://openalex.org/W2962863665","https://openalex.org/W2963238274","https://openalex.org/W2964059111","https://openalex.org/W2966284335","https://openalex.org/W2966559104","https://openalex.org/W2966716789","https://openalex.org/W2966732283","https://openalex.org/W2968356825","https://openalex.org/W2970771982","https://openalex.org/W2971296908","https://openalex.org/W2972458663","https://openalex.org/W2979417040","https://openalex.org/W2985009327","https://openalex.org/W2985411978","https://openalex.org/W2987471611","https://openalex.org/W2988966271","https://openalex.org/W2990673659","https://openalex.org/W2992897306","https://openalex.org/W2998531464","https://openalex.org/W2998702515","https://openalex.org/W3004493192","https://openalex.org/W3005920931","https://openalex.org/W3009459039","https://openalex.org/W3010156198","https://openalex.org/W3011807731","https://openalex.org/W3013103751","https://openalex.org/W3014705052","https://openalex.org/W3022460540","https://openalex.org/W3029701880","https://openalex.org/W3034997167","https://openalex.org/W3035622304","https://openalex.org/W3036586801","https://openalex.org/W3040266635","https://openalex.org/W3042609801","https://openalex.org/W3045786285","https://openalex.org/W3047375952","https://openalex.org/W3079713928","https://openalex.org/W3082197983","https://openalex.org/W3086836049","https://openalex.org/W3089931876","https://openalex.org/W3091662078","https://openalex.org/W3091739674","https://openalex.org/W3092962901","https://openalex.org/W3098448896","https://openalex.org/W3099734810","https://openalex.org/W3105771849","https://openalex.org/W3105977086","https://openalex.org/W3106020963","https://openalex.org/W3118813946","https://openalex.org/W3123375411","https://openalex.org/W3126834903","https://openalex.org/W3128691395","https://openalex.org/W3135550350","https://openalex.org/W3137838319","https://openalex.org/W3155638005","https://openalex.org/W3157897821","https://openalex.org/W3158459113","https://openalex.org/W3161168558","https://openalex.org/W3164942072","https://openalex.org/W3164952570","https://openalex.org/W3165456129","https://openalex.org/W3174036215","https://openalex.org/W3175303557","https://openalex.org/W3181586662","https://openalex.org/W3185425515","https://openalex.org/W3186434753","https://openalex.org/W3191403450","https://openalex.org/W3194730353","https://openalex.org/W3196743233","https://openalex.org/W3198089153","https://openalex.org/W3199693282","https://openalex.org/W3201561610","https://openalex.org/W3204662696","https://openalex.org/W3206274777","https://openalex.org/W3207970821","https://openalex.org/W4200457408","https://openalex.org/W4205563824","https://openalex.org/W4206031975","https://openalex.org/W4206256522","https://openalex.org/W4210726935","https://openalex.org/W4212863985","https://openalex.org/W4214585162","https://openalex.org/W4214810197","https://openalex.org/W4214938700","https://openalex.org/W4220836561","https://openalex.org/W4220891756","https://openalex.org/W4220991771","https://openalex.org/W4221158456","https://openalex.org/W4223522460","https://openalex.org/W4235539094","https://openalex.org/W4240301789","https://openalex.org/W4243565423","https://openalex.org/W4281294571","https://openalex.org/W4282038795","https://openalex.org/W4285338394","https://openalex.org/W4288087455","https://openalex.org/W4293238659","https://openalex.org/W4303614602","https://openalex.org/W4308641647","https://openalex.org/W4312106785","https://openalex.org/W4313433600","https://openalex.org/W4319300518","https://openalex.org/W4321448364","https://openalex.org/W4323824555","https://openalex.org/W4384345694","https://openalex.org/W4385412165","https://openalex.org/W4386591587","https://openalex.org/W4388422146","https://openalex.org/W4402460553","https://openalex.org/W6600050674","https://openalex.org/W6600164255","https://openalex.org/W6600281463","https://openalex.org/W6601208025","https://openalex.org/W6601409588","https://openalex.org/W6602989878","https://openalex.org/W6608548112","https://openalex.org/W6610335769","https://openalex.org/W6636177537","https://openalex.org/W6637681330","https://openalex.org/W6718508100","https://openalex.org/W6822332844","https://openalex.org/W6931474775"],"related_works":["https://openalex.org/W4200065965","https://openalex.org/W2129543081","https://openalex.org/W2085472103","https://openalex.org/W2281933227","https://openalex.org/W2567700705","https://openalex.org/W3124148945","https://openalex.org/W4286214506","https://openalex.org/W2167191881","https://openalex.org/W4389574659","https://openalex.org/W3005406415"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":21},{"year":2025,"cited_by_count":54},{"year":2024,"cited_by_count":9}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}