{"id":"https://openalex.org/W3165292502","doi":"https://doi.org/10.1145/3468264.3468537","title":"Bias in machine learning software: why? how? what to do?","display_name":"Bias in machine learning software: why? how? what to do?","publication_year":2021,"publication_date":"2021-08-18","ids":{"openalex":"https://openalex.org/W3165292502","doi":"https://doi.org/10.1145/3468264.3468537","mag":"3165292502"},"language":"en","primary_location":{"id":"doi:10.1145/3468264.3468537","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3468264.3468537","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2105.12195","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Joymallya Chakraborty","orcid":null},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joymallya Chakraborty","raw_affiliation_strings":["North Carolina State University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"North Carolina State University, USA","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Suvodeep Majumder","orcid":null},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Suvodeep Majumder","raw_affiliation_strings":["North Carolina State University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"North Carolina State University, USA","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"last","author":{"id":null,"display_name":"Tim Menzies","orcid":"https://orcid.org/0000-0002-5040-3196"},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tim Menzies","raw_affiliation_strings":["North Carolina State University, USA"],"raw_orcid":"https://orcid.org/0000-0002-5040-3196","affiliations":[{"raw_affiliation_string":"North Carolina State University, USA","institution_ids":["https://openalex.org/I137902535"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I137902535"],"apc_list":null,"apc_paid":null,"fwci":21.5165,"has_fulltext":false,"cited_by_count":170,"citation_normalized_percentile":{"value":0.99531219,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"429","last_page":"440"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10883","display_name":"Ethics and Social Impacts of AI","score":0.9955000281333923,"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"}},"topics":[{"id":"https://openalex.org/T10883","display_name":"Ethics and Social Impacts of AI","score":0.9955000281333923,"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"}},{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9902999997138977,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.989300012588501,"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/recall","display_name":"Recall","score":0.5397999882698059},{"id":"https://openalex.org/keywords/root","display_name":"Root (linguistics)","score":0.5253999829292297},{"id":"https://openalex.org/keywords/affect","display_name":"Affect (linguistics)","score":0.5163999795913696},{"id":"https://openalex.org/keywords/debiasing","display_name":"Debiasing","score":0.41929998993873596},{"id":"https://openalex.org/keywords/gender-bias","display_name":"Gender bias","score":0.3882000148296356},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.3824000060558319},{"id":"https://openalex.org/keywords/resolution","display_name":"Resolution (logic)","score":0.37119999527931213},{"id":"https://openalex.org/keywords/selection-bias","display_name":"Selection bias","score":0.3628000020980835}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6003999710083008},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5884000062942505},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.5397999882698059},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5389999747276306},{"id":"https://openalex.org/C171078966","wikidata":"https://www.wikidata.org/wiki/Q111029","display_name":"Root (linguistics)","level":2,"score":0.5253999829292297},{"id":"https://openalex.org/C2776035688","wikidata":"https://www.wikidata.org/wiki/Q1606558","display_name":"Affect (linguistics)","level":2,"score":0.5163999795913696},{"id":"https://openalex.org/C2779458634","wikidata":"https://www.wikidata.org/wiki/Q24963715","display_name":"Debiasing","level":2,"score":0.41929998993873596},{"id":"https://openalex.org/C2983427547","wikidata":"https://www.wikidata.org/wiki/Q93200","display_name":"Gender bias","level":2,"score":0.3882000148296356},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.3824000060558319},{"id":"https://openalex.org/C138268822","wikidata":"https://www.wikidata.org/wiki/Q1051925","display_name":"Resolution (logic)","level":2,"score":0.37119999527931213},{"id":"https://openalex.org/C40423286","wikidata":"https://www.wikidata.org/wiki/Q284172","display_name":"Selection bias","level":2,"score":0.3628000020980835},{"id":"https://openalex.org/C134801348","wikidata":"https://www.wikidata.org/wiki/Q7140425","display_name":"Non-response bias","level":2,"score":0.3431999981403351},{"id":"https://openalex.org/C79585631","wikidata":"https://www.wikidata.org/wiki/Q431498","display_name":"Confirmation bias","level":2,"score":0.33410000801086426},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.3327000141143799},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.32739999890327454},{"id":"https://openalex.org/C159447121","wikidata":"https://www.wikidata.org/wiki/Q490535","display_name":"Response bias","level":2,"score":0.3237999975681305},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3174000084400177},{"id":"https://openalex.org/C189216375","wikidata":"https://www.wikidata.org/wiki/Q1127759","display_name":"Cognitive bias","level":3,"score":0.3000999987125397},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.289900004863739},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.2840000092983246},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.27399998903274536},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.27300000190734863},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2712000012397766},{"id":"https://openalex.org/C98559332","wikidata":"https://www.wikidata.org/wiki/Q492762","display_name":"Recall bias","level":2,"score":0.2669999897480011},{"id":"https://openalex.org/C88629717","wikidata":"https://www.wikidata.org/wiki/Q17056323","display_name":"Information bias","level":3,"score":0.2667999863624573}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3468264.3468537","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3468264.3468537","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2105.12195","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2105.12195","pdf_url":"https://arxiv.org/pdf/2105.12195","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2105.12195","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2105.12195","pdf_url":"https://arxiv.org/pdf/2105.12195","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2059141064","https://openalex.org/W2097246321","https://openalex.org/W2116984840","https://openalex.org/W2148143831","https://openalex.org/W2730550703","https://openalex.org/W2759641418","https://openalex.org/W2809701591","https://openalex.org/W2898851569","https://openalex.org/W2967682612","https://openalex.org/W3002398329","https://openalex.org/W3027373771","https://openalex.org/W3032152562","https://openalex.org/W3038416089"],"related_works":[],"abstract_inverted_index":{"Increasingly,":[0],"software":[1],"is":[2,70,193],"making":[3],"autonomous":[4],"decisions":[5,22,95],"in":[6,55,130,163,182,204],"case":[7],"of":[8,20,62,75,90,165,178,184,186,195],"criminal":[9],"sentencing,":[10],"approving":[11],"credit":[12],"cards,":[13],"hiring":[14],"employees,":[15],"and":[16,25,77,103,117,133,167,189],"so":[17],"on.":[18],"Some":[19],"these":[21],"show":[23],"bias":[24,44,76,91,150,200],"adversely":[26],"affect":[27],"certain":[28],"social":[29],"groups":[30],"(e.g.":[31],"those":[32,109],"defined":[33],"by":[34],"sex,":[35],"race,":[36],"age,":[37],"marital":[38],"status).":[39],"Many":[40],"prior":[41,94,152],"works":[42],"on":[43,124,199],"mitigation":[45,201],"take":[46],"the":[47,51,87,93,105,176,196,205],"following":[48],"form:":[49],"change":[50],"data":[52,100],"or":[53],"learners":[54,188],"multiple":[56],"ways,":[57],"then":[58,78],"see":[59],"if":[60],"any":[61],"that":[63,86,96,122,141],"improves":[64],"fairness.":[65],"Perhaps":[66],"a":[67],"better":[68],"approach":[69],"to":[71,108],"postulate":[72],"root":[73,88],"causes":[74,89],"applying":[79],"some":[80],"resolution":[81],"strategy.":[82],"This":[83],"paper":[84],"postulates":[85],"are":[92,128],"affect-":[97],"(a)":[98],"what":[99],"was":[101,139,144],"selected":[102],"(b)":[104],"labels":[106],"assigned":[107],"examples.":[110],"Our":[111],"Fair-SMOTE":[112,158],"algorithm":[113],"removes":[114],"biased":[115],"labels;":[116],"rebalances":[118],"internal":[119],"distributions":[120],"such":[121],"based":[123],"sensitive":[125],"attribute,":[126],"examples":[127],"equal":[129],"both":[131],"positive":[132],"negative":[134],"classes.":[135],"On":[136],"testing,":[137],"it":[138],"seen":[140],"this":[142,191],"method":[143],"just":[145],"as":[146,151],"effective":[147],"at":[148],"reducing":[149],"approaches.":[153],"Further,":[154],"models":[155],"generated":[156],"via":[157],"achieve":[159],"higher":[160],"performance":[161],"(measured":[162],"terms":[164,183],"recall":[166],"F1)":[168],"than":[169],"other":[170],"state-of-the-art":[171],"fairness":[172],"improvement":[173],"algorithms.":[174],"To":[175],"best":[177],"our":[179],"knowledge,":[180],"measured":[181],"number":[185],"analyzed":[187],"datasets,":[190],"study":[192],"one":[194],"largest":[197],"studies":[198],"yet":[202],"presented":[203],"literature.":[206]},"counts_by_year":[{"year":2026,"cited_by_count":16},{"year":2025,"cited_by_count":52},{"year":2024,"cited_by_count":47},{"year":2023,"cited_by_count":41},{"year":2022,"cited_by_count":13},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2021-06-07T00:00:00"}