{"id":"https://openalex.org/W4319736227","doi":"https://doi.org/10.1145/3583561","title":"A Comprehensive Empirical Study of Bias Mitigation Methods for Machine Learning Classifiers","display_name":"A Comprehensive Empirical Study of Bias Mitigation Methods for Machine Learning Classifiers","publication_year":2023,"publication_date":"2023-02-09","ids":{"openalex":"https://openalex.org/W4319736227","doi":"https://doi.org/10.1145/3583561"},"language":"en","primary_location":{"id":"doi:10.1145/3583561","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3583561","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3583561","source":{"id":"https://openalex.org/S142627899","display_name":"ACM Transactions on Software Engineering and Methodology","issn_l":"1049-331X","issn":["1049-331X","1557-7392"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Software Engineering and Methodology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3583561","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031457464","display_name":"Zhenpeng Chen","orcid":"https://orcid.org/0000-0002-4765-1893"},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Zhenpeng Chen","raw_affiliation_strings":["University College London"],"affiliations":[{"raw_affiliation_string":"University College London","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088708850","display_name":"Jie M. Zhang","orcid":"https://orcid.org/0000-0003-0481-7264"},"institutions":[{"id":"https://openalex.org/I183935753","display_name":"King's College London","ror":"https://ror.org/0220mzb33","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I183935753"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jie M. Zhang","raw_affiliation_strings":["King\u2019s College London"],"affiliations":[{"raw_affiliation_string":"King\u2019s College London","institution_ids":["https://openalex.org/I183935753"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012165852","display_name":"Federica Sarro","orcid":"https://orcid.org/0000-0002-9146-442X"},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Federica Sarro","raw_affiliation_strings":["University College London"],"affiliations":[{"raw_affiliation_string":"University College London","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000019783","display_name":"Mark Harman","orcid":"https://orcid.org/0000-0002-5864-4488"},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mark Harman","raw_affiliation_strings":["University College London"],"affiliations":[{"raw_affiliation_string":"University College London","institution_ids":["https://openalex.org/I45129253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5031457464"],"corresponding_institution_ids":["https://openalex.org/I45129253"],"apc_list":null,"apc_paid":null,"fwci":14.9815,"has_fulltext":true,"cited_by_count":87,"citation_normalized_percentile":{"value":0.9931096,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"32","issue":"4","first_page":"1","last_page":"30"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9969000220298767,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9969000220298767,"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/T10883","display_name":"Ethics and Social Impacts of AI","score":0.9898999929428101,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8241164684295654},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.549721360206604},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5429380536079407},{"id":"https://openalex.org/keywords/empirical-research","display_name":"Empirical research","score":0.4398340582847595},{"id":"https://openalex.org/keywords/fairness-measure","display_name":"Fairness measure","score":0.4297291934490204},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42228221893310547},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3550630807876587},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.14376196265220642},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07841894030570984}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8241164684295654},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.549721360206604},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5429380536079407},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.4398340582847595},{"id":"https://openalex.org/C11867375","wikidata":"https://www.wikidata.org/wiki/Q5430671","display_name":"Fairness measure","level":4,"score":0.4297291934490204},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42228221893310547},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3550630807876587},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.14376196265220642},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07841894030570984},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3583561","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3583561","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3583561","source":{"id":"https://openalex.org/S142627899","display_name":"ACM Transactions on Software Engineering and Methodology","issn_l":"1049-331X","issn":["1049-331X","1557-7392"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Software Engineering and Methodology","raw_type":"journal-article"},{"id":"pmh:oai:kclpure.kcl.ac.uk:openaire/8748b47e-6278-45ee-be57-b95f8b7cff0d","is_oa":true,"landing_page_url":"https://kclpure.kcl.ac.uk/portal/en/publications/8748b47e-6278-45ee-be57-b95f8b7cff0d","pdf_url":"https://arxiv.org/pdf/2207.03277.pdf","source":{"id":"https://openalex.org/S4306400216","display_name":"Research Portal (King's College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I183935753","host_organization_name":"King's College London","host_organization_lineage":["https://openalex.org/I183935753"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Chen, Z, Zhang, J, Sarro, F & Harman, M 2023, 'A Comprehensive Empirical Study of Bias Mitigation Methods for Machine Learning Classifiers', ACM TRANSACTIONS ON SOFTWARE ENGINEERING AND METHODOLOGY, vol. 32, no. 4, 106. https://doi.org/10.1145/3583561","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"doi:10.1145/3583561","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3583561","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3583561","source":{"id":"https://openalex.org/S142627899","display_name":"ACM Transactions on Software Engineering and Methodology","issn_l":"1049-331X","issn":["1049-331X","1557-7392"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Software Engineering and Methodology","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.6100000143051147,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G4223508424","display_name":null,"funder_award_id":"EP/V026801/2","funder_id":"https://openalex.org/F4320314731","funder_display_name":"UK Research and Innovation"},{"id":"https://openalex.org/G4336396751","display_name":null,"funder_award_id":"EP/V026801","funder_id":"https://openalex.org/F4320314731","funder_display_name":"UK Research and Innovation"}],"funders":[{"id":"https://openalex.org/F4320314731","display_name":"UK Research and Innovation","ror":"https://ror.org/001aqnf71"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4319736227.pdf","grobid_xml":"https://content.openalex.org/works/W4319736227.grobid-xml"},"referenced_works_count":65,"referenced_works":["https://openalex.org/W1556779599","https://openalex.org/W1961345416","https://openalex.org/W1972978214","https://openalex.org/W1979769549","https://openalex.org/W1996406592","https://openalex.org/W2010490953","https://openalex.org/W2014352947","https://openalex.org/W2094947835","https://openalex.org/W2097246321","https://openalex.org/W2116666691","https://openalex.org/W2116984840","https://openalex.org/W2118020653","https://openalex.org/W2138428785","https://openalex.org/W2150997454","https://openalex.org/W2599025709","https://openalex.org/W2604738573","https://openalex.org/W2730550703","https://openalex.org/W2759641418","https://openalex.org/W2794373096","https://openalex.org/W2809701591","https://openalex.org/W2891197287","https://openalex.org/W2893425640","https://openalex.org/W2913668833","https://openalex.org/W2913771223","https://openalex.org/W2954384356","https://openalex.org/W2963100392","https://openalex.org/W2963116854","https://openalex.org/W2964031043","https://openalex.org/W2967682612","https://openalex.org/W2999309192","https://openalex.org/W3002398329","https://openalex.org/W3007157104","https://openalex.org/W3009290003","https://openalex.org/W3014437350","https://openalex.org/W3027373771","https://openalex.org/W3032152562","https://openalex.org/W3038416089","https://openalex.org/W3098260236","https://openalex.org/W3098524120","https://openalex.org/W3099376688","https://openalex.org/W3100111264","https://openalex.org/W3101079689","https://openalex.org/W3103741452","https://openalex.org/W3105507623","https://openalex.org/W3119800663","https://openalex.org/W3122215046","https://openalex.org/W3135028703","https://openalex.org/W3156188980","https://openalex.org/W3165292502","https://openalex.org/W3166873126","https://openalex.org/W3179976352","https://openalex.org/W3181414820","https://openalex.org/W3193448347","https://openalex.org/W3194157648","https://openalex.org/W3194588521","https://openalex.org/W4206787394","https://openalex.org/W4210736086","https://openalex.org/W4242337985","https://openalex.org/W4284709622","https://openalex.org/W4289751798","https://openalex.org/W4296422519","https://openalex.org/W4299627282","https://openalex.org/W4308641598","https://openalex.org/W4308643061","https://openalex.org/W4388229648"],"related_works":["https://openalex.org/W2361713743","https://openalex.org/W2138888940","https://openalex.org/W2136050782","https://openalex.org/W2147625294","https://openalex.org/W2144132509","https://openalex.org/W2374431462","https://openalex.org/W2057526413","https://openalex.org/W2961085424","https://openalex.org/W2002544160","https://openalex.org/W4286571664"],"abstract_inverted_index":{"Software":[0],"bias":[1,21,66,89,113,141,164,192,226],"is":[2,57,190],"an":[3],"increasingly":[4],"important":[5,81],"operational":[6],"concern":[7],"for":[8,24],"software":[9,51,82],"engineers.":[10],"We":[11,84],"present":[12],"a":[13],"large-scale,":[14],"comprehensive":[15],"empirical":[16,55],"study":[17],"of":[18,43,65,98,127,156,162,173,179,216],"17":[19],"representative":[20],"mitigation":[22,67,90,114,142,165,193,227],"methods":[23,91,115,143,166,213],"Machine":[25],"Learning":[26],"(ML)":[27],"classifiers,":[28],"evaluated":[29],"with":[30],"11":[31],"ML":[32,94,108,152,186],"performance":[33,95,109,153],"metrics":[34,124,180],"(e.g.,":[35],"accuracy),":[36],"4":[37,122],"fairness":[38,118,137,150,184],"metrics,":[39,70],"and":[40,71,151,176,185,220],"20":[41],"types":[42],"fairness-performance":[44,72],"tradeoff":[45,73,200],"assessment,":[46],"applied":[47],"to":[48,76,106,135,146,182,223,231],"8":[49],"widely-adopted":[50],"decision":[52],"tasks.":[53],"The":[54,205],"coverage":[56],"much":[58],"more":[59],"comprehensive,":[60],"covering":[61],"the":[62,88,99,112,121,129,140,157,160,163,171,177,198,203,217,225],"largest":[63],"numbers":[64],"methods,":[68],"evaluation":[69],"measures":[74],"compared":[75],"previous":[77],"work":[78],"on":[79,168],"this":[80],"property.":[83],"find":[85,210],"that":[86,195,208],"(1)":[87],"significantly":[92,116],"decrease":[93,147],"in":[96,125,148,154,201,214],"53%":[97],"studied":[100],"scenarios":[101,130],"(ranging":[102,131],"between":[103,132],"42%\u223c66%":[104],"according":[105,134],"different":[107,136],"metrics);":[110,138],"(2)":[111],"improve":[117],"measured":[119],"by":[120],"used":[123,181],"46%":[126],"all":[128,202],"24%\u223c59%":[133],"(3)":[139],"even":[144],"lead":[145],"both":[149],"25%":[155],"scenarios;":[158],"(4)":[159],"effectiveness":[161],"depends":[167],"tasks,":[169],"models,":[170],"choice":[172],"protected":[174],"attributes,":[175],"set":[178],"assess":[183],"performance;":[187],"(5)":[188],"there":[189],"no":[191],"method":[194,207,228],"can":[196],"achieve":[197],"best":[199,206,229],"scenarios.":[204,218],"we":[209],"outperforms":[211],"other":[212],"30%":[215],"Researchers":[219],"practitioners":[221],"need":[222],"choose":[224],"suited":[230],"their":[232],"intended":[233],"application":[234],"scenario(s).":[235]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":38},{"year":2024,"cited_by_count":37},{"year":2023,"cited_by_count":7}],"updated_date":"2026-04-14T08:04:32.555800","created_date":"2025-10-10T00:00:00"}