[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-120792-en":3,"doc-seo-120792-105":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},120792,8796095360427,"Lucas Martin","https://ap-avatar.wpscdn.com/davatar_994ba38a5ba835b3df7d355c54d3ed8d",8,"Research & Report","Bias Mitigation for Machine Learning Classifiers - A Comprehensive Survey","This paper surveys bias mitigation methods for achieving fairness in machine learning classifiers. A total of 341 publications are collected and organized by intervention procedure—pre-processing, in-processing, and post-processing—and by the specific techniques used. The survey further examines how methods are evaluated in the literature, with emphasis on datasets, fairness metrics, and benchmarking practices. The resulting evidence supports practitioners in selecting appropriate fairness metrics, datasets, and comparison mechanisms when developing and assessing new bias mitigation approaches.","# Bias Mitigation for Machine Learning Classifiers:A ComprehensiveSurvey\n\nMAX HORT,Simula Research Laboratory,Norway  \nZHENPENG CHEN,University College London,United KingdomJIE M.ZHANG,King's College London,United KingdomMARK HARMAN,University College London,United KingdomFEDERICA SARRO,University College London,United Kingdom  \nThis paper provides a comprehensive survey of bias mitigation methods for achieving fairness in Machine Learning(ML)models.We collect a total of341 publications concerning bias mitigation for ML classifiers.These methods can be distinguishedbased on their intervention procedure(ie,pre-processing,in-processing,post-processing)and the technique they apply.Weinvestigate how existing bias mitigation methods are evaluated in the literature.In particular,we consider datasets,metricsand benchmarking.Based on the gathered insights (e.g.,What is the most popular fairness metric?How many datasets areused for evaluating bias mitigation methods?),we hope to support practitioners in making informed choices when developingand evaluating new bias mitigation methods.  \nCCS Concepts:·Computing methodologies→Supervisedlearning by classification;Artificial intelligence.  \nAdditional Key Words and Phrases:fairness,bias mitigation,debiasing,fairness-aware machine learning,classification  \n## 1 INTRODUCTION\n\nMachine Learning(ML)has been increasingly popular in recent years,both in the diversity and importance offapplications [76].ML is used in a variety of critical applications such as justice risk assessments [24,38],jobrecommendations[413],and autonomous driving [227].  \nWhile ML systems have the advantage to relieve humans from tedious tasks and are able to perform complexcalculations at ahigher speed [287],they are only as good as the data on which they are trained [34].MLalgorithms,which are never designed to intentionally incorporate bias,run the risk of replicating or even amplifying biaspresent in real-world data[34,283,348].This may cause unfair treatment in which some individuals or groups ofpeople are privileged(i.e.,receive a favourable treatment)and others are unprivileged(i.e.,receive an unfavourabletreatment).In this context,a fair treatment of individuals constitutes that decisions are made independent ofsensitive attributes such as gender or race,such that individuals are treated based on merit [187,188,256].Forexample,one can aim for an equal probability of population groups to receive a positive treatment,or an equaltreatment of individuals that only differ in sensitive attributes.  \nHuman bias has been transferred to various real-word systems relying on MLand there are many examplesof this in the literature.For instance,bias has been found in advertisement and recruitment processes [93,413],affecting university admissions [41]and human rights [256].Not only is such a biased behaviour undesired,but  \nAuthors'addresses:Max Hort,Simula Research Laboratory,Oslo,Norway,maxh@simulano;Zhenpeng Chen,University College London,London,United Kingdom,zp.chen@ucl.ac.uk;Jie M.Zhang,King's College London,London,United Kingdom,je.zhang@kcl.ac.uk;MarkHarman,University College London,London,United Kingdom,markhaman@ucl.ac.uk;Federica Sarro,University Collge London,London,United Kingdom,f.sarro@ucl.ac.uk.  \nit can fall under regulatory control and risk the violation of anti-discrimination laws [67,283,311],as sensitiveattributes such as age,disability,gender identity,race are protected by US law in the Fair Housing Act and EqualCredit Opportunity Act[212].  \nAnother example for a biased treatment of population groups can be found in the COMPAS(CorrectionalOffender Management Profiling for Alternative Sanctions)software,used by courts in US to determine the risksof an individual to reoffend.These scores are used to motivate decisions on whether and when defendants areto be set free,in different stages of the justice system.Problematically,this software falsely labelled non-whitedefendants with higher risk scores than white ","cbCaifE8qQMcM01P","https://ap.wps.com/l/cbCaifE8qQMcM01P","pdf",722640,1,51,"English","en",105,"# Introduction\n## Bias and unfair treatment in machine learning\n## Bias mitigation categories\n## Goals and contributions of the survey","[{\"question\":\"How do the authors categorize bias mitigation methods for ML classifiers?\",\"answer\":\"They distinguish methods by intervention procedure: pre-processing, in-processing, and post-processing, and also by the techniques applied.\"},{\"question\":\"What does the survey analyze when evaluating bias mitigation methods?\",\"answer\":\"It focuses on evaluation datasets, fairness metrics, and benchmarking approaches used in the literature.\"},{\"question\":\"Why is the survey intended to help practitioners?\",\"answer\":\"It consolidates insights on popular fairness metrics, datasets, and benchmarking choices so practitioners can set up experiments more efficiently when proposing new methods.\"}]","Bias Mitigation for Machine Learning Classifiers - A Comprehensive Survey | PDF",1785732054,129,{"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},"bias-mitigation-for-machine-learning-classifiers-a-comprehensive-survey","",{"@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/bias-mitigation-for-machine-learning-classifiers-a-comprehensive-survey/120792/",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","2026-08-03",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},"How do the authors categorize bias mitigation methods for ML classifiers?","Question",{"text":75,"@type":76},"They distinguish methods by intervention procedure: pre-processing, in-processing, and post-processing, and also by the techniques applied.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What does the survey analyze when evaluating bias mitigation methods?",{"text":80,"@type":76},"It focuses on evaluation datasets, fairness metrics, and benchmarking approaches used in the literature.",{"name":82,"@type":73,"acceptedAnswer":83},"Why is the survey intended to help practitioners?",{"text":84,"@type":76},"It consolidates insights on popular fairness metrics, datasets, and benchmarking choices so practitioners can set up experiments more efficiently when proposing new methods.","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},[93,97,101,105,110,115,120,123,128,131,135],{"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":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]