[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-126544-en":3,"doc-seo-126544-105":31,"detail-sidebar-cat-0-en-105":92},{"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":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":28,"seo_description":14,"update_tm":29,"read_time":30},126544,13056712833777,"Logic","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","Towards Fair Machine Learning Software - Understanding and Addressing Model Bias Through Counterfactual Thinking","Increasing adoption of machine learning (ML) software can produce unfair and unethical outcomes, making fairness bugs an escalating concern in practice. Many fixes reduce model accuracy, trading performance for fairness. The work introduces a counterfactual approach that reasons about bias causes within ML software, avoiding direct bias correction that harms utility. It also integrates models jointly optimized for performance and fairness. Evaluations on 10 benchmark tasks over 8 real-world datasets use performance, fairness, and measurement scenarios, showing strong fairness gains with competitive performance and state-of-the-art superiority in most cases.","Michigan Technological University  \nDigital Commons @ Michigan Tech  \n\n| Michigan Tech Publications, Part 2 |\n| --- |\n| 2-16-2023\u003Cbr>Towards Fair Machine Learning Software: Understanding and Addressing Model Bias Through Counterfactual Thinking\u003Cbr>Zichong Wang\u003Cbr>Michigan Technological University, [zichongw@mtu.edu](zichongw@mtu.edu)\u003Cbr>Yang Zhou\u003Cbr>Singapore Management University\u003Cbr>Meikang Qiu\u003Cbr>Dakota State University\u003Cbr>Israat Haque\u003Cbr>Dalhousie University\u003Cbr>Laura Brown\u003Cbr>Michigan Technological University, [lebrown@mtu.edu](lebrown@mtu.edu)\u003Cbr>See next page for additional authors\u003Cbr>Follow this and additional works at: [https://digitalcommons.mtu.edu/michigantech-p2](https://digitalcommons.mtu.edu/michigantech-p2)\u003Cbr> Part of the Computer Sciences Commons |\n\nRecommended Citation  \nWang, Z., Zhou, Y., Qiu, M., Haque, I., Brown, L., He, Y., Zhang, W., & et al. (2023) . Towards Fair Machine Learning Software: Understanding and Addressing Model Bias Through Counterfactual Thinking. arXiv.  \n[http://doi.org/10.48550/arXiv.2302.08018](http://doi.org/10.48550/arXiv.2302.08018)  \nRetrieved from: [https://digitalcommons.mtu.edu/michigantech-p2/1](https://digitalcommons.mtu.edu/michigantech-p2/1)121  \nFollow this and additional works at: [https://digitalcommons.mtu.edu/michigantech-p2](https://digitalcommons.mtu.edu/michigantech-p2)  \n Part of the Computer Sciences Commons  \nAuthors  \nZichong Wang, Yang Zhou, Meikang Qiu, Israat Haque, Laura Brown, Yi He, Wenbin Zhang, and et al.  \nThis article is available at Digital Commons @ Michigan Tech: [https://digitalcommons.mtu.edu/michigantech-p2/](https://digitalcommons.mtu.edu/michigantech-p2/)[ ](https://digitalcommons.mtu.edu/michigantech-p2/)1121  \nTowards Fair Machine Learning Software: Understanding and Addressing Model Bias Through Counterfactual Thinking  \nZichong Wang  \n[zichongw@mtu.edu](zichongw@mtu.edu)[ ](zichongw@mtu.edu)Michigan Technological University Houghton, Michigan, USA  \nYang Zhou  \n[zyang@smu.edu.sg](zyang@smu.edu.sg)[ ](zyang@smu.edu.sg)Singapore Management University Singapore, Singapore  \nMeikang Qiu  \n[qiumeikang@yahoo.com](qiumeikang@yahoo.com)[ ](qiumeikang@yahoo.com)Dakota State University Madison, South Dakota, USA  \narXiv :2302 .08018v1 [ cs . SE] 16 Feb 2023  \nIsraat Haque  \n[israat@dal.ca](israat@dal.ca)[ ](israat@dal.ca)Dalhousie University Halifax, Nova Scotia, Canada  \nJianwu Wang  \n[jianwu@umbc.edu](jianwu@umbc.edu)[ ](jianwu@umbc.edu)University of Maryland, Baltimore County Baltimore, Maryland, USA  \nLaura Brown  \n[lebrown@mtu.edu](lebrown@mtu.edu)[ ](lebrown@mtu.edu)Michigan Technological University Houghton, Michigan, USA  \nDavid Lo  \n[davidlo@smu.edu.sg](davidlo@smu.edu.sg)[ ](davidlo@smu.edu.sg)Singapore Management University Singapore, Singapore  \nYi He  \n[yihe@cs.odu.edu](yihe@cs.odu.edu)[ ](yihe@cs.odu.edu)Old Dominion University Norfolk, Virginia, USA  \nWenbin Zhang  \n[wenbinzh@mtu.edu](wenbinzh@mtu.edu)[ ](wenbinzh@mtu.edu)Michigan Technological University Houghton, Michigan, USA  \nABSTRACT  \nThe increasing use of Machine Learning (ML) software can lead to unfair and unethical decisions, thus fairness bugs in software are becoming a growing concern. Addressing these fairness bugs often involves sacrificing ML performance, such as accuracy. To address this issue, we present a novel counterfactual approach that uses counterfactual thinking to tackle the root causes of bias in ML software. In addition, our approach combines models optimized for both performance and fairness, resulting in an optimal solution in both aspects. We conducted a thorough evaluation of our approach on 10 benchmark tasks using a combination of 5 performance metrics, 3 fairness metrics, and 15 measurement scenarios, all applied to 8 real-world datasets. The conducted extensive evaluations show that the proposed method significantly improves the fairness of ML software while maintaining competitive performance, outperforming state-of-the-art solutions in 84.6% of over","cbCaimy2u4897jV0","https://ap.wps.com/l/cbCaimy2u4897jV0","pdf",1781545,4,1,15,"English","en",105,"# Abstract\n# Introduction\n## Background and motivation\n## Fairness bugs and trade-offs","[{\"question\":\"Why do fairness bugs in machine learning software matter?\",\"answer\":\"ML software can drive unfair or unethical decisions, so fairness bugs have become a growing concern in real-world deployment.\"},{\"question\":\"What problem do many existing fairness solutions face?\",\"answer\":\"They often require sacrificing ML performance, such as reducing accuracy, to improve fairness.\"},{\"question\":\"How does the proposed method address model bias?\",\"answer\":\"It uses a counterfactual thinking approach to tackle the root causes of bias in ML software and combines models optimized for both performance and fairness.\"}]","Towards Fair Machine Learning Software - Understanding and Addressing Model Bias Through Counterfactual Thinking | PDF",1785933241,38,{"code":4,"msg":32,"data":33},"ok",{"site_id":25,"language":24,"slug":34,"title":13,"keywords":35,"description":14,"schema_data":36,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":29},"towards-fair-machine-learning-software-understanding-and-addressing-model-bias-through-counterfactual-thinking","",{"@graph":37,"@context":86},[38,54,69],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,49,52],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":48},"https://docshare.wps.com/document/","Document",2,{"item":50,"name":12,"@type":44,"position":51},"https://docshare.wps.com/document/research-report/",3,{"item":53,"name":13,"@type":44,"position":20},"https://docshare.wps.com/document/towards-fair-machine-learning-software-understanding-and-addressing-model-bias-through-counterfactual-thinking/126544/",{"url":53,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":24,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":42,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-24","2026-08-05",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"Why do fairness bugs in machine learning software matter?","Question",{"text":76,"@type":77},"ML software can drive unfair or unethical decisions, so fairness bugs have become a growing concern in real-world deployment.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"What problem do many existing fairness solutions face?",{"text":81,"@type":77},"They often require sacrificing ML performance, such as reducing accuracy, to improve fairness.",{"name":83,"@type":74,"acceptedAnswer":84},"How does the proposed method address model bias?",{"text":85,"@type":77},"It uses a counterfactual thinking approach to tackle the root causes of bias in ML software and combines models optimized for both performance and fairness.","https://schema.org",{"og:url":53,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":53},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":48,"doc_module":4,"doc_module_name":47,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":20,"doc_module":4,"doc_module_name":47,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":47,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":47,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":47,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":47,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":47,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":47,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":47,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]