{"id":"https://openalex.org/W4400878073","doi":"https://doi.org/10.1109/tse.2024.3431445","title":"FairBalance: How to Achieve Equalized Odds With Data Pre-Processing","display_name":"FairBalance: How to Achieve Equalized Odds With Data Pre-Processing","publication_year":2024,"publication_date":"2024-07-22","ids":{"openalex":"https://openalex.org/W4400878073","doi":"https://doi.org/10.1109/tse.2024.3431445"},"language":"en","primary_location":{"id":"doi:10.1109/tse.2024.3431445","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tse.2024.3431445","pdf_url":null,"source":{"id":"https://openalex.org/S8351582","display_name":"IEEE Transactions on Software Engineering","issn_l":"0098-5589","issn":["0098-5589","1939-3520","2326-3881"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Software Engineering","raw_type":"journal-article"},"type":"article","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/A5014850850","display_name":"Zhe Yu","orcid":"https://orcid.org/0000-0002-6841-1725"},"institutions":[{"id":"https://openalex.org/I155173764","display_name":"Rochester Institute of Technology","ror":"https://ror.org/00v4yb702","country_code":"US","type":"education","lineage":["https://openalex.org/I155173764"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhe Yu","raw_affiliation_strings":["Department of Software Engineering, Rochester Institute of Technology, Rochester, NY, USA"],"raw_orcid":"https://orcid.org/0000-0002-6841-1725","affiliations":[{"raw_affiliation_string":"Department of Software Engineering, Rochester Institute of Technology, Rochester, NY, USA","institution_ids":["https://openalex.org/I155173764"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004929245","display_name":"Joymallya Chakraborty","orcid":"https://orcid.org/0000-0003-4651-1837"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joymallya Chakraborty","raw_affiliation_strings":["Amazon, Seattle, WA, USA"],"raw_orcid":"https://orcid.org/0000-0003-4651-1837","affiliations":[{"raw_affiliation_string":"Amazon, Seattle, WA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077008083","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":["Department of Computer Science, North Carolina State University, Raleigh, NC, USA"],"raw_orcid":"https://orcid.org/0000-0002-5040-3196","affiliations":[{"raw_affiliation_string":"Department of Computer Science, North Carolina State University, Raleigh, NC, USA","institution_ids":["https://openalex.org/I137902535"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.4444,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.94789711,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"50","issue":"9","first_page":"2294","last_page":"2312"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11891","display_name":"Big Data and Business Intelligence","score":0.3330000042915344,"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"}},"topics":[{"id":"https://openalex.org/T11891","display_name":"Big Data and Business Intelligence","score":0.3330000042915344,"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":0.8515785932540894},{"id":"https://openalex.org/keywords/odds","display_name":"Odds","score":0.45335474610328674},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.1286720633506775},{"id":"https://openalex.org/keywords/logistic-regression","display_name":"Logistic regression","score":0.08772137761116028}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8515785932540894},{"id":"https://openalex.org/C143095724","wikidata":"https://www.wikidata.org/wiki/Q515895","display_name":"Odds","level":3,"score":0.45335474610328674},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.1286720633506775},{"id":"https://openalex.org/C151956035","wikidata":"https://www.wikidata.org/wiki/Q1132755","display_name":"Logistic regression","level":2,"score":0.08772137761116028}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tse.2024.3431445","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tse.2024.3431445","pdf_url":null,"source":{"id":"https://openalex.org/S8351582","display_name":"IEEE Transactions on Software Engineering","issn_l":"0098-5589","issn":["0098-5589","1939-3520","2326-3881"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Software Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":64,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W1961345416","https://openalex.org/W1978813754","https://openalex.org/W2014352947","https://openalex.org/W2116984840","https://openalex.org/W2148143831","https://openalex.org/W2330210193","https://openalex.org/W2400239131","https://openalex.org/W2759641418","https://openalex.org/W2762694293","https://openalex.org/W2809878087","https://openalex.org/W2901823434","https://openalex.org/W2962769166","https://openalex.org/W2963100392","https://openalex.org/W2963116854","https://openalex.org/W2991598122","https://openalex.org/W2998936266","https://openalex.org/W3002248449","https://openalex.org/W3002398329","https://openalex.org/W3005040148","https://openalex.org/W3005597817","https://openalex.org/W3008843783","https://openalex.org/W3008907338","https://openalex.org/W3027373771","https://openalex.org/W3032152562","https://openalex.org/W3032966140","https://openalex.org/W3038416089","https://openalex.org/W3094239814","https://openalex.org/W3098869601","https://openalex.org/W3099376688","https://openalex.org/W3103741452","https://openalex.org/W3120740533","https://openalex.org/W3127299232","https://openalex.org/W3152436735","https://openalex.org/W3156188980","https://openalex.org/W3165292502","https://openalex.org/W3166873126","https://openalex.org/W3176008422","https://openalex.org/W3179976352","https://openalex.org/W3181414820","https://openalex.org/W3193448347","https://openalex.org/W3194157648","https://openalex.org/W3194588521","https://openalex.org/W4220820301","https://openalex.org/W4284681038","https://openalex.org/W4284709622","https://openalex.org/W4289258088","https://openalex.org/W4289438483","https://openalex.org/W4308641598","https://openalex.org/W4312890174","https://openalex.org/W6637373629","https://openalex.org/W6684072790","https://openalex.org/W6728551298","https://openalex.org/W6746225964","https://openalex.org/W6748377460","https://openalex.org/W6754734166","https://openalex.org/W6755765851","https://openalex.org/W6765646913","https://openalex.org/W6768690664","https://openalex.org/W6774548214","https://openalex.org/W6778746080","https://openalex.org/W6809846253","https://openalex.org/W6838798272","https://openalex.org/W7014198846"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W1604849300","https://openalex.org/W4231328776","https://openalex.org/W2766061861","https://openalex.org/W1604293003","https://openalex.org/W1979850356","https://openalex.org/W3005040438","https://openalex.org/W3132387835","https://openalex.org/W2910024633"],"abstract_inverted_index":{"This":[0],"research":[1],"seeks":[2],"to":[3,17,52,117,170,202,234],"benefit":[4],"the":[5,46,60,89,97,106,110,124,144,165,191,203,219,235],"software":[6,35,50,55,63],"engineering":[7],"society":[8],"by":[9,57,198],"providing":[10],"a":[11,93,135,186],"simple":[12],"yet":[13],"effective":[14],"pre-processing":[15,187,221],"approach":[16],"achieve":[18],"equalized":[19,73,84,113,140,155,227,246],"odds":[20,85,114,141,156,159,228],"fairness":[21],"in":[22,127,194,243],"machine":[23,33,61],"learning":[24,34,62,90],"software.":[25],"Fairness":[26],"issues":[27],"have":[28],"attracted":[29],"increasing":[30],"attention":[31],"since":[32],"is":[36,45,134],"increasingly":[37],"used":[38],"for":[39,82,138,154],"high-stakes":[40],"and":[41,115,252],"high-risk":[42],"decisions.":[43],"It":[44],"responsibility":[47],"of":[48,109,112,245],"all":[49],"developers":[51],"make":[53],"their":[54],"accountable":[56],"ensuring":[58],"that":[59,122],"do":[64],"not":[65,172],"perform":[66],"differently":[67],"on":[68,180],"different":[69],"sensitive":[70],"demographic":[71,129,196],"groups\u2014satisfying":[72],"odds.":[74,247],"Different":[75],"from":[76],"prior":[77],"works":[78],"which":[79,189],"either":[80],"optimize":[81],"an":[83,150],"related":[86],"metric":[87],"during":[88],"process":[91],"like":[92],"black-box,":[94],"or":[95],"manipulate":[96],"training":[98,146,204],"data":[99],"following":[100],"some":[101],"intuition;":[102],"this":[103],"work":[104],"studies":[105],"root":[107],"cause":[108],"violation":[111],"how":[116],"tackle":[118],"it.":[119],"We":[120],"found":[121],"equalizing":[123],"class":[125,166,192],"distribution":[126,193],"each":[128,195],"group":[130,197],"with":[131],"sample":[132],"weights":[133,201],"necessary":[136],"condition":[137,153],"achieving":[139],"without":[142,229],"modifying":[143],"normal":[145],"process.":[147],"In":[148],"addition,":[149],"important":[151],"partial":[152],"(zero":[157],"average":[158],"difference)":[160],"can":[161,224],"be":[162,171],"guaranteed":[163],"when":[164],"distributions":[167],"are":[168],"weighted":[169],"only":[173],"equal":[174],"but":[175],"also":[176,238],"balanced":[177],"(1:1).":[178],"Based":[179],"these":[181],"analyses,":[182],"we":[183,254],"proposed":[184,220],"FairBalance,":[185],"algorithm":[188,222],"balances":[190],"assigning":[199],"calculated":[200],"data.":[205],"On":[206],"eight":[207],"real-world":[208],"datasets,":[209],"our":[210,256],"empirical":[211],"results":[212],"show":[213],"that,":[214],"at":[215],"low":[216],"computational":[217],"overhead,":[218],"FairBalance":[223,237],"significantly":[225],"improve":[226],"much,":[230],"if":[231],"any":[232],"damage":[233],"utility.":[236],"outperforms":[239],"existing":[240],"state-of-the-art":[241],"approaches":[242],"terms":[244],"To":[248],"facilitate":[249],"reuse,":[250],"reproduction,":[251],"validation,":[253],"made":[255],"scripts":[257],"available":[258],"athttps://github.com/hil-se/FairBalance.":[259]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}