{"id":"https://openalex.org/W2795539379","doi":"https://doi.org/10.3390/sym10040099","title":"How to Address the Data Quality Issues in Regression Models: A Guided Process for Data Cleaning","display_name":"How to Address the Data Quality Issues in Regression Models: A Guided Process for Data Cleaning","publication_year":2018,"publication_date":"2018-04-06","ids":{"openalex":"https://openalex.org/W2795539379","doi":"https://doi.org/10.3390/sym10040099","mag":"2795539379"},"language":"en","primary_location":{"id":"doi:10.3390/sym10040099","is_oa":true,"landing_page_url":"https://doi.org/10.3390/sym10040099","pdf_url":"https://www.mdpi.com/2073-8994/10/4/99/pdf?version=1525347389","source":{"id":"https://openalex.org/S190787756","display_name":"Symmetry","issn_l":"2073-8994","issn":["2073-8994"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Symmetry","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2073-8994/10/4/99/pdf?version=1525347389","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058031153","display_name":"David Camilo Corrales","orcid":"https://orcid.org/0000-0003-4717-3040"},"institutions":[{"id":"https://openalex.org/I152650591","display_name":"University of Cauca","ror":"https://ror.org/04fybn584","country_code":"CO","type":"education","lineage":["https://openalex.org/I152650591"]},{"id":"https://openalex.org/I50357001","display_name":"Universidad Carlos III de Madrid","ror":"https://ror.org/03ths8210","country_code":"ES","type":"education","lineage":["https://openalex.org/I50357001"]}],"countries":["CO","ES"],"is_corresponding":true,"raw_author_name":"David Corrales","raw_affiliation_strings":["Departamento de Ciencias de la Computaci\u00f3n e Ingenier\u00eda, Universidad Carlos III de Madrid, Avenida de la Universidad, 30, 28911 Legan\u00e9s, Spain","Grupo de Ingenier\u00eda Telem\u00e1tica, Universidad del Cauca, Campus Tulc\u00e1n, 190002 Popay\u00e1n, Colombia"],"affiliations":[{"raw_affiliation_string":"Departamento de Ciencias de la Computaci\u00f3n e Ingenier\u00eda, Universidad Carlos III de Madrid, Avenida de la Universidad, 30, 28911 Legan\u00e9s, Spain","institution_ids":["https://openalex.org/I50357001"]},{"raw_affiliation_string":"Grupo de Ingenier\u00eda Telem\u00e1tica, Universidad del Cauca, Campus Tulc\u00e1n, 190002 Popay\u00e1n, Colombia","institution_ids":["https://openalex.org/I152650591"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084306663","display_name":"Juan Carlos Corrales","orcid":"https://orcid.org/0000-0002-5608-9097"},"institutions":[{"id":"https://openalex.org/I152650591","display_name":"University of Cauca","ror":"https://ror.org/04fybn584","country_code":"CO","type":"education","lineage":["https://openalex.org/I152650591"]}],"countries":["CO"],"is_corresponding":false,"raw_author_name":"Juan Corrales","raw_affiliation_strings":["Grupo de Ingenier\u00eda Telem\u00e1tica, Universidad del Cauca, Campus Tulc\u00e1n, 190002 Popay\u00e1n, Colombia"],"affiliations":[{"raw_affiliation_string":"Grupo de Ingenier\u00eda Telem\u00e1tica, Universidad del Cauca, Campus Tulc\u00e1n, 190002 Popay\u00e1n, Colombia","institution_ids":["https://openalex.org/I152650591"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059348719","display_name":"Agapito Ledezma","orcid":"https://orcid.org/0000-0002-0041-6829"},"institutions":[{"id":"https://openalex.org/I50357001","display_name":"Universidad Carlos III de Madrid","ror":"https://ror.org/03ths8210","country_code":"ES","type":"education","lineage":["https://openalex.org/I50357001"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Agapito Ledezma","raw_affiliation_strings":["Departamento de Ciencias de la Computaci\u00f3n e Ingenier\u00eda, Universidad Carlos III de Madrid, Avenida de la Universidad, 30, 28911 Legan\u00e9s, Spain"],"affiliations":[{"raw_affiliation_string":"Departamento de Ciencias de la Computaci\u00f3n e Ingenier\u00eda, Universidad Carlos III de Madrid, Avenida de la Universidad, 30, 28911 Legan\u00e9s, Spain","institution_ids":["https://openalex.org/I50357001"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5058031153"],"corresponding_institution_ids":["https://openalex.org/I152650591","https://openalex.org/I50357001"],"apc_list":{"value":2000,"currency":"CHF","value_usd":2165},"apc_paid":{"value":2000,"currency":"CHF","value_usd":2165},"fwci":5.0742,"has_fulltext":true,"cited_by_count":59,"citation_normalized_percentile":{"value":0.95319988,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"10","issue":"4","first_page":"99","last_page":"99"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9986000061035156,"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":0.9986000061035156,"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":0.989799976348877,"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"}},{"id":"https://openalex.org/T11891","display_name":"Big Data and Business Intelligence","score":0.9805999994277954,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7712536454200745},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.6949231624603271},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.6394062638282776},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5944486856460571},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5566544532775879},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5206767320632935},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.5200814604759216},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.42202863097190857},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3554685115814209},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.289731502532959},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10517489910125732}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7712536454200745},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6949231624603271},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.6394062638282776},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5944486856460571},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5566544532775879},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5206767320632935},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.5200814604759216},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.42202863097190857},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3554685115814209},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.289731502532959},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10517489910125732},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3390/sym10040099","is_oa":true,"landing_page_url":"https://doi.org/10.3390/sym10040099","pdf_url":"https://www.mdpi.com/2073-8994/10/4/99/pdf?version=1525347389","source":{"id":"https://openalex.org/S190787756","display_name":"Symmetry","issn_l":"2073-8994","issn":["2073-8994"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Symmetry","raw_type":"journal-article"},{"id":"pmh:oai:e-archivo.uc3m.es:10016/28063","is_oa":false,"landing_page_url":"http://hdl.handle.net/10016/28063","pdf_url":null,"source":{"id":"https://openalex.org/S4306400817","display_name":"e-Archivo (Carlos III University of Madrid)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I50357001","host_organization_name":"Universidad Carlos III de Madrid","host_organization_lineage":["https://openalex.org/I50357001"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:doaj.org/article:ea4b0ca132254ac7b665ab0aa8ca7e92","is_oa":true,"landing_page_url":"https://doaj.org/article/ea4b0ca132254ac7b665ab0aa8ca7e92","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Symmetry, Vol 10, Iss 4, p 99 (2018)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/2073-8994/10/4/99/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/sym10040099","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Symmetry; Volume 10; Issue 4; Pages: 99","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/sym10040099","is_oa":true,"landing_page_url":"https://doi.org/10.3390/sym10040099","pdf_url":"https://www.mdpi.com/2073-8994/10/4/99/pdf?version=1525347389","source":{"id":"https://openalex.org/S190787756","display_name":"Symmetry","issn_l":"2073-8994","issn":["2073-8994"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Symmetry","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.5,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[{"id":"https://openalex.org/G5396905545","display_name":null,"funder_award_id":"TRA2015-63708-R","funder_id":"https://openalex.org/F4320323770","funder_display_name":"Universidad Carlos III de Madrid"},{"id":"https://openalex.org/G5874396204","display_name":null,"funder_award_id":"TRA2016-78886-C3-1-R","funder_id":"https://openalex.org/F4320323770","funder_display_name":"Universidad Carlos III de Madrid"}],"funders":[{"id":"https://openalex.org/F4320309955","display_name":"Departamento Administrativo de Ciencia, Tecnolog\u00eda e Innovaci\u00f3n (COLCIENCIAS)","ror":"https://ror.org/048jthh02"},{"id":"https://openalex.org/F4320323364","display_name":"Universidad del Cauca","ror":"https://ror.org/04fybn584"},{"id":"https://openalex.org/F4320323770","display_name":"Universidad Carlos III de Madrid","ror":"https://ror.org/03ths8210"},{"id":"https://openalex.org/F4320326262","display_name":"Ministerio de Asuntos Econ\u00f3micos y Transformaci\u00f3n Digital, Gobierno de Espa\u00f1a","ror":"https://ror.org/03sv46s19"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2795539379.pdf","grobid_xml":"https://content.openalex.org/works/W2795539379.grobid-xml"},"referenced_works_count":83,"referenced_works":["https://openalex.org/W91659207","https://openalex.org/W114024208","https://openalex.org/W1491282455","https://openalex.org/W1494072001","https://openalex.org/W1497617446","https://openalex.org/W1503167101","https://openalex.org/W1505365525","https://openalex.org/W1608549042","https://openalex.org/W1619226191","https://openalex.org/W1673310716","https://openalex.org/W1831050183","https://openalex.org/W1949265207","https://openalex.org/W1970498130","https://openalex.org/W1975938969","https://openalex.org/W1979719735","https://openalex.org/W1986332411","https://openalex.org/W2006398000","https://openalex.org/W2006407062","https://openalex.org/W2020191321","https://openalex.org/W2039015671","https://openalex.org/W2040884411","https://openalex.org/W2049058890","https://openalex.org/W2051725773","https://openalex.org/W2071114814","https://openalex.org/W2076170369","https://openalex.org/W2087016914","https://openalex.org/W2119387367","https://openalex.org/W2121973001","https://openalex.org/W2122646361","https://openalex.org/W2122777273","https://openalex.org/W2124316743","https://openalex.org/W2127415865","https://openalex.org/W2134256069","https://openalex.org/W2136691316","https://openalex.org/W2146759849","https://openalex.org/W2151580670","https://openalex.org/W2151818224","https://openalex.org/W2154846261","https://openalex.org/W2155399784","https://openalex.org/W2157894025","https://openalex.org/W2157954477","https://openalex.org/W2158939484","https://openalex.org/W2167025863","https://openalex.org/W2167101736","https://openalex.org/W2195118355","https://openalex.org/W2255742114","https://openalex.org/W2275507448","https://openalex.org/W2286513919","https://openalex.org/W2304359685","https://openalex.org/W2319278070","https://openalex.org/W2346663430","https://openalex.org/W2402277527","https://openalex.org/W2462125907","https://openalex.org/W2472882072","https://openalex.org/W2496713576","https://openalex.org/W2500453565","https://openalex.org/W2547942448","https://openalex.org/W2552500151","https://openalex.org/W2574666645","https://openalex.org/W2585502432","https://openalex.org/W2586350499","https://openalex.org/W2789687532","https://openalex.org/W2802209325","https://openalex.org/W2998216295","https://openalex.org/W3151822565","https://openalex.org/W4205930639","https://openalex.org/W4237625490","https://openalex.org/W4244908355","https://openalex.org/W4247793074","https://openalex.org/W4254182148","https://openalex.org/W4291302748","https://openalex.org/W4321613415","https://openalex.org/W6604735148","https://openalex.org/W6630161315","https://openalex.org/W6631263138","https://openalex.org/W6636336243","https://openalex.org/W6638324127","https://openalex.org/W6639468679","https://openalex.org/W6640462745","https://openalex.org/W6699936050","https://openalex.org/W6733261796","https://openalex.org/W6758972637","https://openalex.org/W7066667914"],"related_works":["https://openalex.org/W4234711916","https://openalex.org/W2027108423","https://openalex.org/W2135768893","https://openalex.org/W1855666948","https://openalex.org/W2758561209","https://openalex.org/W3021414116","https://openalex.org/W176219849","https://openalex.org/W1548095260","https://openalex.org/W2094985717","https://openalex.org/W2343361478"],"abstract_inverted_index":{"Today,":[0],"data":[1,27,36,52,60,72,77,94,101,111,121,129,153],"availability":[2],"has":[3],"gone":[4],"from":[5,62,139],"scarce":[6],"to":[7,39,165,196],"superabundant.":[8],"Technologies":[9],"like":[10],"IoT,":[11],"trends":[12],"in":[13,54,123],"social":[14,67],"media":[15],"and":[16,23,49],"the":[17,59,76,82,91,106,110,140,148,152,156,167,173,182,186,200],"capabilities":[18],"of":[19,26,35,51,75,93,109,143,150,175],"smart-phones":[20],"are":[21,191],"producing":[22],"digitizing":[24],"lots":[25],"that":[28,158,197],"was":[29,163],"previously":[30],"unavailable.":[31],"This":[32,86],"massive":[33],"increase":[34],"creates":[37],"opportunities":[38],"gain":[40],"new":[41,47],"business":[42],"models,":[43],"but":[44],"also":[45],"demands":[46],"techniques":[48],"methods":[50],"quality":[53,73,102],"knowledge":[55],"discovery,":[56],"especially":[57],"when":[58],"comes":[61],"different":[63],"sources":[64],"(e.g.,":[65],"sensors,":[66],"networks,":[68],"cameras,":[69],"etc.).":[70],"The":[71,127,178],"process":[74,119,131],"set":[78],"proposes":[79],"conclusions":[80],"about":[81],"information":[83],"they":[84],"contain.":[85],"is":[87,103,132,159],"increasingly":[88],"done":[89],"with":[90,185],"aid":[92],"cleaning":[95,122,130,154],"approaches.":[96],"Therefore,":[97],"guaranteeing":[98],"a":[99,118,135],"high":[100],"considered":[104],"as":[105],"primary":[107],"goal":[108],"scientist.":[112],"In":[113],"this":[114],"paper,":[115],"we":[116],"propose":[117],"for":[120],"regression":[124,169],"models":[125,170,184],"(DC-RM).":[126],"proposed":[128,171],"evaluated":[133],"through":[134],"real":[136],"datasets":[137],"coming":[138],"UCI":[141,176],"Repository":[142],"Machine":[144],"Learning":[145],"Databases.":[146],"With":[147],"aim":[149],"assessing":[151],"process,":[155],"dataset":[157,187],"cleaned":[160],"by":[161,172,181,189,199],"DC-RM":[162,190],"used":[164],"train":[166],"same":[168],"authors":[174],"datasets.":[177],"results":[179],"achieved":[180],"trained":[183],"produced":[188],"better":[192],"than":[193],"or":[194],"equal":[195],"presented":[198],"datasets\u2019":[201],"authors.":[202]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":4}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}
