[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-116921-en":3,"doc-seo-116921-105":30,"detail-sidebar-cat-0-en-105":87},{"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},116921,549758146520,"Patrick","https://ap-avatar.wpscdn.com/avatar/80002397d8c0411e94?_k=1775819394049821470",8,"Research & Report","Locating disparities in machine learning - Automatic Location of Disparities (ALD) framework","Machine learning can produce predictions with disparate outcomes that systematically disadvantage population subgroups defined by sensitive attributes such as age, gender, or related characteristics. Meeting upcoming legal and regulatory requirements requires practical methods to locate such disparities, especially when sensitive attributes are not specified in advance and data are high-dimensional. The proposed Automatic Location of Disparities (ALD) framework is data-driven, supports diverse classifier types, multiple disparity definitions, and handles categorical and continuous predictors, including intersectional effects. ALD outputs interpretable audit reports and is validated on synthetic and real-world datasets to enable effective detection and mitigation of discrimination.","Locating disparities in machine learning  \nMoritz von Zahn  \n[vzahn@wiwi.uni-frankfurt.de](vzahn@wiwi.uni-frankfurt.de)[ ](vzahn@wiwi.uni-frankfurt.de)Goethe University Frankfurt Germany  \nOliver Hinz  \n[hinz@wiwi.uni-frankfurt.de](hinz@wiwi.uni-frankfurt.de)[ ](hinz@wiwi.uni-frankfurt.de)Goethe University Frankfurt Germany  \nStefan Feuerriegel  \n[feuerriegel@lmu.de](feuerriegel@lmu.de)[ ](feuerriegel@lmu.de)LMU Munich Germany  \narXiv :2208 .06680v 3 [ cs .LG] 4 Sep 2023  \nABSTRACT  \nMachine learning can provide predictions with disparate outcomes, in which subgroups of the population (e. g., defined by age, gender, or other sensitive attributes) are systematically disadvantaged. In order to comply with upcoming legislation, practitioners need to locate such disparate outcomes. However, previous literature typically detects disparities through statistical procedures for when the sensitive attribute is specified a priori. This limits applicability in real-world settings where datasets are high dimensional and, on top of that, sensitive attributes may be unknown. As a remedy, we propose a data-driven framework called Automatic Location of Disparities (ALD) which aims at locating disparities in machine learning. ALD meets several demands from industry: ALD (1) is applicable to arbitrary machine learning classifiers; (2) operates on different definitions of disparities (e. g., statistical parity or equalized odds); (3) deals with both categorical and continuous predictorseven if disparities arise from complex and multi-way interactions known as intersectionality (e. g., age above 60 and female) . ALD produces interpretable audit reports as output. We demonstrate the effectiveness of ALD based on both synthetic and real-world datasets. As a result, we empower practitioners to effectively locate and mitigate disparities in machine learning algorithms, conduct algorithmic audits, and protect individuals from discrimination.  \nCCS CONCEPTS  \n• Computing methodologies → Machine learning; Classification and regression trees; • Social and professional topics → User characteristics; • Applied computing → Law, social and behavioral sciences.  \nKEYWORDS  \nalgorithmic fairness, algorithmic bias, fairness detection, tree algorithm, recursive partitioning, machine learning  \nACM Reference Format:  \nMoritz von Zahn, Oliver Hinz, and Stefan Feuerriegel. 2023. Locating disparities in machine learning. In Proceedings of ACM Conference (Conference’17) . ACM, New York, NY, USA, 12 pages. [https://doi.org/10.1145/nnnnnnn.nnnnnnn](https://doi.org/10.1145/nnnnnnn.nnnnnnn)  \n1 INTRODUCTION  \nMachine learning (ML) is nowadays widely used by companies and organizations. However, ML is known to be subject to bias (c.f.[7]) . This refers to disparities in which outcomes of ML systematically deviate from statistical, moral, or regulatory standards [19], especially in ways that disadvantage people from certain sociodemographics (gender, race, or other attributes deemed sensitive) . For  \nConference’17, July 2017, Washington, DC, USA 2023. ACM ISBN 978-x-xxxx-xxxx-x/YY/MM. . . $15.00 [https://doi.org/10.1145/nnnnnnn.nnnnnnn](https://doi.org/10.1145/nnnnnnn.nnnnnnn)  \nexample, ML in criminal justice has been found to return output with systematic disadvantages towards black defendants [4] . Specifically, the COMPAS algorithm falsely labels black defendants as“high risk” more frequently than white defendants, potentially leading to a disproportionate number of black defendants being kept in prison. Systematic disadvantages have been found in various industry applications of ML, such as lending [30], marketing [52], and automated hiring [43] .  \nCompanies are increasingly under pressure to assess potential disparities in their ML applications due to legal concerns. For example, in June 2023, the European Parliament approved the AI Act that specifically demands “bias monitoring [and] detection” [23] for multiple types of ML applications in industry. Comparable leg","cbCaipaKCm2IT3aJ","https://ap.wps.com/l/cbCaipaKCm2IT3aJ","pdf",992009,1,12,"English","en",105,"# Introduction\n## Disparate outcomes and bias in ML\n## Regulatory pressure and auditing needs\n## Challenges when sensitive attributes are unknown\n# Automatic Location of Disparities (ALD)","[{\"question\":\"What problem does the paper address in machine learning applications?\",\"answer\":\"It addresses how machine learning can yield disparate outcomes that systematically disadvantage certain subgroups, creating risk under legal and regulatory requirements. The focus is on locating these disparities for algorithmic auditing.\"},{\"question\":\"How are the results validated and what is the output of ALD?\",\"answer\":\"The effectiveness of ALD is demonstrated using both synthetic and real-world datasets. It produces interpretable audit reports intended to help practitioners detect and mitigate discrimination.\"}]","Locating disparities in machine learning - Automatic Location of Disparities (ALD) framework | PDF",1785672537,30,{"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":82,"head_meta":84,"extra_data":86,"updated_unix":28},"locating-disparities-in-machine-learning-automatic-location-of-disparities-ald-framework","",{"@graph":36,"@context":81},[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/locating-disparities-in-machine-learning-automatic-location-of-disparities-ald-framework/116921/",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","2026-08-02",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does the paper address in machine learning applications?","Question",{"text":75,"@type":76},"It addresses how machine learning can yield disparate outcomes that systematically disadvantage certain subgroups, creating risk under legal and regulatory requirements. The focus is on locating these disparities for algorithmic auditing.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How are the results validated and what is the output of ALD?",{"text":80,"@type":76},"The effectiveness of ALD is demonstrated using both synthetic and real-world datasets. It produces interpretable audit reports intended to help practitioners detect and mitigate discrimination.","https://schema.org",{"og:url":52,"og:type":83,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":85,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":88},[89,93,97,101,106,111,116,118,123,126,130],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":90,"show_sort_weight":91,"slug":92},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Exam",70,"exam",{"id":102,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},5,"Comic",60,"comic",{"id":107,"doc_module":4,"doc_module_name":46,"category_name":108,"show_sort_weight":109,"slug":110},6,"Technology",50,"technology",{"id":112,"doc_module":4,"doc_module_name":46,"category_name":113,"show_sort_weight":114,"slug":115},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":29,"slug":117},"research-report",{"id":119,"doc_module":4,"doc_module_name":46,"category_name":120,"show_sort_weight":121,"slug":122},9,"Religion & Spirituality",20,"religion-spirituality",{"id":121,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":121,"slug":125},"World Cup","world-cup",{"id":127,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":127,"slug":129},10,"Lifestyle","lifestyle",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":102,"slug":133},19,"General","general"]