[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-122729-en":3,"doc-seo-122729-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},122729,34359740700684,"Finn","https://ap-avatar.wpscdn.com/avatar/1f400023980c374ae676?_k=1777273430885731487",8,"Research & Report","Not So Fair - The Impact of Presumably Fair Machine Learning Models","Bias mitigation methods are often used to make machine learning models fairer in classification settings, but this practice rests on the assumption that disadvantaged groups fare better than they would without mitigation. A “fair” outcome does not guarantee beneficial effects for a disadvantaged individual, who may still experience negative impact. The work models and examines these impacts, investigating whether mitigated models can harm disadvantaged individuals and identifying the conditions that drive such effects using a loan repayment case.","King’s Research Portal  \nDocument Version  \nPeer reviewed version  \nLink to publication record in King's Research Portal  \nCitation for published version (APA):  \nJorgensen, M. , Richert, H. , Black, E. , Criado, N. , & Such, J. (2023) . Not So Fair: The Impact of Presumably Fair Machine Learning Models. In Proceedings of the 2023 AAAI/ACM Conference on AI, Ethics, and Society ACM.  \nCiting this paper  \nPlease note that where the full-text provided on King's Research Portal is the Author Accepted Manuscript or Post-Print version this may differ from the final Published version. If citing, it is advised that you check and use the publisher's definitive version for pagination, volume/issue, and date of publication details. And where the final published version is provided on the Research Portal, if citing you are again advised to check the publisher's website for any subsequent corrections.  \nGeneral rights  \nCopyright and moral rights for the publications made accessible in the Research Portal are retained by the authors and/or other copyright owners and it is a condition of accessing publications that users recognize and abide by the legal requirements associated with these rights.  \n•Users may download and print one copy of any publication from the Research Portal for the purpose of private study or research.  \n•You may not further distribute the material or use it for any profit-making activity or commercial gain  \n•You may freely distribute the URL identifying the publication in the Research Portal  \nTake down policy  \nIf you believe that this document breaches copyright please contact [librarypure@kcl.ac.uk](librarypure@kcl.ac.uk) providing details, and we will remove access to the work immediately and investigate your claim.  \nDownload date: 06. Oct. 2023  \nNot So Fair: The Impact of Presumably Fair Machine Learning  \nModels  \nMackenzie Jorgensen  \n[mackenzie.jorgensen@kcl.ac.uk](mackenzie.jorgensen@kcl.ac.uk)[ ](mackenzie.jorgensen@kcl.ac.uk)King’s College London London, UK  \nHannah Richert  \n[hrichert@uni-osnabrueck.de](hrichert@uni-osnabrueck.de)[ ](hrichert@uni-osnabrueck.de)Universität Osnabrück Osnabrück, Germany  \nElizabeth Black  \n[elizabeth.black@kcl.ac.uk](elizabeth.black@kcl.ac.uk)[ ](elizabeth.black@kcl.ac.uk)King’s College London London, UK  \nNatalia Criado  \n[ncriado@upv.es](ncriado@upv.es)[ ](ncriado@upv.es)Universidad Politècnica de València  \nValència, Spain  \nJose Such  \n[jose.such@kcl.ac.uk](jose.such@kcl.ac.uk)[ ](jose.such@kcl.ac.uk)King’s College London London, UK  \nABSTRACT  \nWhen bias mitigation methods are applied to make fairer machine learning models in fairness-related classification settings, there isan assumption that the disadvantaged group should be better off than if no mitigation method was applied. However, this is a potentially dangerous assumption because a “fair” model outcome does not automatically imply a positive impact for a disadvantaged individual—they could still be negatively impacted. Modeling and accounting for those impacts is key to ensure that mitigated models are not unintentionally harming individuals; we investigate if mitigated models can still negatively impact disadvantaged individuals and what conditions affect those impacts in a loan repayment example. Our results show that most mitigated models negatively impact disadvantaged group members in comparison to the unmitigated models. The domain-dependent impacts of model outcomes should help drive future bias mitigation method development.  \nCCS CONCEPTS  \n• Computing methodologies → Machine learning; • Social and professional topics → User characteristics.  \nKEYWORDS  \nfairness, impact, machine learning, synthetic data  \nACM Reference Format:  \nMackenzie Jorgensen, Hannah Richert, Elizabeth Black, Natalia Criado, and Jose Such. 2023. Not So Fair: The Impact of Presumably Fair Machine Learning Models. In AAAI/ACM Conference on AI, Ethics, and Society (AIES’23), August 8–10, 2023, Montréal, QC, Canada. ACM, New York, ","cbCaicuw6uichT3T","https://ap.wps.com/l/cbCaicuw6uichT3T","pdf",1734256,1,16,"English","en",105,"# Abstract\n# Introduction","[{\"question\":\"Why can “presumably fair” machine learning models still harm disadvantaged individuals?\",\"answer\":\"Bias mitigation may improve fairness metrics, but fairness outcomes do not automatically translate into positive real-world effects for disadvantaged people, who can still be negatively impacted.\"},{\"question\":\"What does the study investigate regarding mitigated models?\",\"answer\":\"It examines whether mitigated models can still negatively impact disadvantaged individuals and what conditions determine the presence and nature of these impacts.\"},{\"question\":\"How are the findings supported in the paper?\",\"answer\":\"The analysis uses a loan repayment example to evaluate impacts and compares mitigated models against unmitigated models.\"}]","Not So Fair - The Impact of Presumably Fair Machine Learning Models | PDF",1785812560,40,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"not-so-fair-the-impact-of-presumably-fair-machine-learning-models","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/not-so-fair-the-impact-of-presumably-fair-machine-learning-models/122729/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-04",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why can “presumably fair” machine learning models still harm disadvantaged individuals?","Question",{"text":75,"@type":76},"Bias mitigation may improve fairness metrics, but fairness outcomes do not automatically translate into positive real-world effects for disadvantaged people, who can still be negatively impacted.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What does the study investigate regarding mitigated models?",{"text":80,"@type":76},"It examines whether mitigated models can still negatively impact disadvantaged individuals and what conditions determine the presence and nature of these impacts.",{"name":82,"@type":73,"acceptedAnswer":83},"How are the findings supported in the paper?",{"text":84,"@type":76},"The analysis uses a loan repayment example to evaluate impacts and compares mitigated models against unmitigated models.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,119,122,127,130,134],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":29,"slug":118},7,"Healthcare","healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]