{"id":"https://openalex.org/W2942649361","doi":"https://doi.org/10.1145/3310986.3311023","title":"Empirical Comparison of Area under ROC curve (AUC) and Mathew Correlation Coefficient (MCC) for Evaluating Machine Learning Algorithms on Imbalanced Datasets for Binary Classification","display_name":"Empirical Comparison of Area under ROC curve (AUC) and Mathew Correlation Coefficient (MCC) for Evaluating Machine Learning Algorithms on Imbalanced Datasets for Binary Classification","publication_year":2019,"publication_date":"2019-01-25","ids":{"openalex":"https://openalex.org/W2942649361","doi":"https://doi.org/10.1145/3310986.3311023","mag":"2942649361"},"language":"en","primary_location":{"id":"doi:10.1145/3310986.3311023","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3310986.3311023","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd International Conference on Machine Learning and Soft Computing","raw_type":"proceedings-article"},"type":"conference-paper","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/A5013719253","display_name":"Halimu Chongomweru","orcid":"https://orcid.org/0000-0003-0374-8287"},"institutions":[{"id":"https://openalex.org/I200859690","display_name":"Universiti Teknologi Brunei","ror":"https://ror.org/004y7f915","country_code":"BN","type":"education","lineage":["https://openalex.org/I200859690"]}],"countries":["BN"],"is_corresponding":false,"raw_author_name":"Chongomweru Halimu","raw_affiliation_strings":["Universiti Teknologi Brunei, School of Computing and Informatics, Jalan Tungku Link Gadong BE"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universiti Teknologi Brunei, School of Computing and Informatics, Jalan Tungku Link Gadong BE","institution_ids":["https://openalex.org/I200859690"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101855513","display_name":"Asem Kasem","orcid":"https://orcid.org/0000-0001-8871-3117"},"institutions":[{"id":"https://openalex.org/I200859690","display_name":"Universiti Teknologi Brunei","ror":"https://ror.org/004y7f915","country_code":"BN","type":"education","lineage":["https://openalex.org/I200859690"]}],"countries":["BN"],"is_corresponding":false,"raw_author_name":"Asem Kasem","raw_affiliation_strings":["Universiti Teknologi Brunei, School of Computing and Informatics, Jalan Tungku Link Gadong BE"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universiti Teknologi Brunei, School of Computing and Informatics, Jalan Tungku Link Gadong BE","institution_ids":["https://openalex.org/I200859690"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056577173","display_name":"S. H. Shah Newaz","orcid":"https://orcid.org/0000-0001-7453-5268"},"institutions":[{"id":"https://openalex.org/I200859690","display_name":"Universiti Teknologi Brunei","ror":"https://ror.org/004y7f915","country_code":"BN","type":"education","lineage":["https://openalex.org/I200859690"]}],"countries":["BN"],"is_corresponding":false,"raw_author_name":"S. H. Shah Newaz","raw_affiliation_strings":["Universiti Teknologi Brunei, School of Computing and Informatics, Jalan Tungku Link Gadong BE"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universiti Teknologi Brunei, School of Computing and Informatics, Jalan Tungku Link Gadong BE","institution_ids":["https://openalex.org/I200859690"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I200859690"],"apc_list":null,"apc_paid":null,"fwci":4.6722,"has_fulltext":false,"cited_by_count":136,"citation_normalized_percentile":{"value":0.96189442,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9998999834060669,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9865999817848206,"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/T11396","display_name":"Artificial Intelligence in Healthcare","score":0.9805999994277954,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/receiver-operating-characteristic","display_name":"Receiver operating characteristic","score":0.718662679195404},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6926301717758179},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6852495074272156},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.62247234582901},{"id":"https://openalex.org/keywords/correlation","display_name":"Correlation","score":0.5892614722251892},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5774790644645691},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.521070122718811},{"id":"https://openalex.org/keywords/binary-classification","display_name":"Binary classification","score":0.5170374512672424},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4902077317237854},{"id":"https://openalex.org/keywords/matthews-correlation-coefficient","display_name":"Matthews correlation coefficient","score":0.4627665579319},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.43239784240722656},{"id":"https://openalex.org/keywords/area-under-curve","display_name":"Area under curve","score":0.41719865798950195},{"id":"https://openalex.org/keywords/correlation-coefficient","display_name":"Correlation coefficient","score":0.410061240196228},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.30083945393562317},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.2606044113636017}],"concepts":[{"id":"https://openalex.org/C58471807","wikidata":"https://www.wikidata.org/wiki/Q327120","display_name":"Receiver operating characteristic","level":2,"score":0.718662679195404},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6926301717758179},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6852495074272156},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.62247234582901},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.5892614722251892},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5774790644645691},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.521070122718811},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.5170374512672424},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4902077317237854},{"id":"https://openalex.org/C164085508","wikidata":"https://www.wikidata.org/wiki/Q4811327","display_name":"Matthews correlation coefficient","level":3,"score":0.4627665579319},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.43239784240722656},{"id":"https://openalex.org/C3020225094","wikidata":"https://www.wikidata.org/wiki/Q80091","display_name":"Area under curve","level":3,"score":0.41719865798950195},{"id":"https://openalex.org/C2780092901","wikidata":"https://www.wikidata.org/wiki/Q3433612","display_name":"Correlation coefficient","level":2,"score":0.410061240196228},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.30083945393562317},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.2606044113636017},{"id":"https://openalex.org/C112705442","wikidata":"https://www.wikidata.org/wiki/Q323936","display_name":"Pharmacokinetics","level":2,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"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/C126322002","wikidata":"https://www.wikidata.org/wiki/Q11180","display_name":"Internal medicine","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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:10.1145/3310986.3311023","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3310986.3311023","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd International Conference on Machine Learning and Soft Computing","raw_type":"proceedings-article"},{"id":"mag:3217438745","is_oa":false,"landing_page_url":"https://jglobal.jst.go.jp/en/detail?JGLOBAL_ID=202002231567249808","pdf_url":null,"source":{"id":"https://openalex.org/S4306500161","display_name":"ACM Proceedings","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":"ACM Proceedings","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7200000286102295,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1514907448","https://openalex.org/W1524761913","https://openalex.org/W1680392829","https://openalex.org/W1912982817","https://openalex.org/W2021560851","https://openalex.org/W2096451472","https://openalex.org/W2109553965","https://openalex.org/W2119168155","https://openalex.org/W2141307855","https://openalex.org/W2153915640","https://openalex.org/W2155653793","https://openalex.org/W2158698691","https://openalex.org/W2182722412","https://openalex.org/W2334028018","https://openalex.org/W2539380934","https://openalex.org/W2544836728","https://openalex.org/W2562319768","https://openalex.org/W2606176882","https://openalex.org/W2620760558","https://openalex.org/W2808979505"],"related_works":["https://openalex.org/W3108466129","https://openalex.org/W2940055329","https://openalex.org/W2011314675","https://openalex.org/W2903708425","https://openalex.org/W3179518614","https://openalex.org/W3046905389","https://openalex.org/W4287760213","https://openalex.org/W3034642336","https://openalex.org/W3216067289","https://openalex.org/W4200065130"],"abstract_inverted_index":{"A":[0],"common":[1],"challenge":[2],"encountered":[3],"when":[4,22,103,189],"trying":[5],"to":[6,53,73,90,100,137,161,198],"perform":[7],"classifications":[8],"and":[9,48,96,133,169,207],"comparing":[10,125,208],"classifiers":[11],"is":[12,19,65,89,179,187],"selecting":[13],"a":[14,111,200],"suitable":[15],"performance":[16],"metric.":[17],"This":[18,195],"particularly":[20],"important":[21],"the":[23,30,41,75,78,84,129],"data":[24],"has":[25,36,70],"class-imbalance":[26],"problems.":[27],"Area":[28],"under":[29],"Receiver":[31],"Operating":[32],"Characteristic":[33],"Curve":[34],"(AUC)":[35],"been":[37,71],"commonly":[38],"used":[39,104],"by":[40],"machine":[42,107,148],"learning":[43,108,149],"community":[44],"in":[45,60,205],"such":[46],"situations,":[47],"recently":[49],"researchers":[50],"are":[51,98,171],"starting":[52],"use":[54],"Matthew":[55],"Correlation":[56],"Coefficient":[57],"(MCC),":[58],"especially":[59],"biomedical":[61],"research.":[62],"However,":[63],"there":[64],"no":[66],"empirical":[67],"study":[68,88],"that":[69,166],"conducted":[72],"compare":[74,138],"suitability":[76],"of":[77,86,113,131,135],"two":[79],"metrics.":[80],"In":[81,116],"this":[82,87],"paper,":[83],"aim":[85],"provide":[91],"insights":[92],"about":[93],"how":[94],"AUC":[95,139,168,178,197],"MCC":[97,170,204],"compared":[99],"each":[101,175],"other":[102],"with":[105,155,174],"classical":[106],"algorithms":[109,150],"over":[110],"range":[112],"imbalanced":[114,153],"datasets.":[115,194],"our":[117],"study,":[118],"we":[119],"utilize":[120],"an":[121],"earlier-proposed":[122],"criteria":[123],"for":[124],"metrics":[126],"based":[127],"on":[128,151,191],"degree":[130,134],"consistency":[132],"Discriminancy":[136],"against":[140],"MCC.":[141,183],"We":[142],"carry":[143],"out":[144],"experiments":[145],"using":[146],"four":[147],"54":[152],"datasets,":[154],"imbalance":[156],"ratios":[157],"ranging":[158],"from":[159],"1%":[160],"10%.":[162],"The":[163,184],"results":[164],"demonstrate":[165],"both":[167],"statistically":[172],"consistent":[173],"other;":[176],"however":[177],"more":[180],"discriminating":[181],"than":[182,203],"same":[185],"observation":[186],"noticed":[188],"evaluated":[190],"23":[192],"balanced":[193],"suggests":[196],"be":[199],"better":[201],"measure":[202],"evaluating":[206],"classification":[209],"algorithms.":[210]},"counts_by_year":[{"year":2026,"cited_by_count":9},{"year":2025,"cited_by_count":25},{"year":2024,"cited_by_count":34},{"year":2023,"cited_by_count":25},{"year":2022,"cited_by_count":20},{"year":2021,"cited_by_count":16},{"year":2020,"cited_by_count":7}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}