[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-121770-en":3,"doc-seo-121770-105":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},121770,8796095360427,"Lucas Martin","https://ap-avatar.wpscdn.com/davatar_994ba38a5ba835b3df7d355c54d3ed8d",8,"Research & Report","Detection and Evaluation of bias-inducing Features in Machine learning","Cause-to-effect analysis enables decomposition of likely causes behind undesirable outcomes and supports ranking causes for prioritizing fixes, simplifying complex problems, and visualizing their relationships. In machine learning, it helps explain biased system behavior by tracing root causes through features. This work supports systematic discovery of bias-inducing features without requiring prior identification of sensitive attributes, reducing the risk of missing relevant sources of bias. It also supports fair decision-making by letting domain experts judge whether bias from specific features is acceptable.","arXiv :2310 . 12805v1 [ cs .LG] 19 Oct 2023  \nNoname manuscript No.  \n(will be inserted by the editor)  \nDetection and Evaluation of bias-inducing Features in Machine learning  \nMoses Openja · Gabriel Laberge ·  \nFoutse Khomh  \nAccepted: October 18, 2023  \nAbstract The cause-to-effect analysis can help us decompose all the likely causes of a problem, such as an undesirable business situation or unintended harm to the individual(s) . This implies that we can identify how the problems are inherited, rank the causes to help prioritize fixes, simplify a complex problem and visualize them. In the context of machine learning (ML), one can use cause-to-effect analysis to understand the reason for the biased behavior of the system. For example, we can examine the root causes of biases by checking each feature for a potential cause of bias in the model. To approach this, one can apply small changes to a given feature or a pair of features in the data, following some guidelines and observing how it impacts the decision made by the model (i.e., model prediction) . Therefore, we can use cause-to-effect analysis to identify the potential bias-inducing features, even when these features are originally are unknown. This is important since most current methods require a pre-identification of sensitive features for bias assessment and can actually miss other relevant bias-inducing features, which is why systematic identification of such features is necessary. Moreover, it often occurs that to achieve an equitable outcome, one has to take into account sensitive features in the model decision. Therefore, it should be up to the domain experts to decide based on their knowledge of the context of a decision whether bias induced by specific features is acceptable or not. In this study, we propose an  \nM. Openja Polytechnique Montreal Tel.: +(1)438-505 5297  \nE-mail: [openja.moses@polymtl.ca](openja.moses@polymtl.ca)[ ](openja.moses@polymtl.ca)[G. Laberge](G. Laberge)  \nPolytechnique Montreal  \nE-mail: [gabriel.laberg@polymtl.ca](gabriel.laberg@polymtl.ca)  \nF. Khomh  \nPolytechnique Montreal  \nE-mail: [foutse.khomh@polymtl.ca](foutse.khomh@polymtl.ca)  \napproach for systematically identifying all bias-inducing features of a model to help support the decision-making of domain experts. Our technique is based on the idea of swapping the values of the features and computing the divergencesin the distribution of the model prediction using different distance functions. We evaluated our technique using four well-known datasets to showcase how our contribution can help spearhead the standard procedure when developing, testing, maintaining, and deploying fair/equitable machine learning systems.  \nKeywords Machine learning · Bias · Fairness · Sensitive features  \n1 Introduction  \nThe use of machine learning (ML) systems is permeating every aspect of our life, such as healthcare (e.g., the presence of heart disease [25,4]), autonomous systems, education, banking (e.g. , loan approval, or marketing campaigns [53]), recruitment, and court justice to assess the likelihood that a defendant recommits a crime. These systems are trained on data that are usually biased towards some features, leading to the biased behavior of the resulting model. For example, the COMPAS (Correctional Offender Management Profiling for Alternative Sanctions) algorithm for scoring defendants was found to be biased in the sense of having different False Positive Rates between white and black sub-populations. The Gender Shades project [15], commercial facial recognition systems, is found to be biased towards the dark skinned women, or gender bias in the Google neural machine translation models [42], among others. The above examples highlight the importance of quantifying whether machine learning systems exhibit biased behavior that impacts some individuals.  \nIn the recent years, the researchers have been proposing methods such as [5, 17,61,41,33,63,21] to test if a model is making a fairer ","cbCainiTsfLmljzy","https://ap.wps.com/l/cbCainiTsfLmljzy","pdf",919618,1,65,"English","en",105,"# Introduction\n## Importance of bias quantification in ML systems\n## Fairness evaluation when sensitive features are known or unknown\n# Proposed approach: systematic identification of bias-inducing features\n## Feature swapping and divergence-based evaluation","[{\"question\":\"Why is cause-to-effect analysis useful for studying bias in machine learning models?\",\"answer\":\"It helps break down likely causes of an undesirable outcome and connects biased behavior to underlying factors. In ML, this supports identifying how features contribute to biased predictions by analyzing root causes.\"},{\"question\":\"What problem does the study address regarding fairness assessment?\",\"answer\":\"Current methods often require pre-identifying sensitive features for bias assessment and may miss other bias-inducing features. The study aims for systematic identification even when such sensitive features are unknown.\"},{\"question\":\"How does the proposed technique identify bias-inducing features?\",\"answer\":\"It swaps feature values and computes divergences in the distribution of model predictions using different distance functions. This reveals features whose changes materially affect predictive behavior.\"}]","Detection and Evaluation of bias-inducing Features in Machine learning | PDF",1785806752,164,{"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},"detection-and-evaluation-of-bias-inducing-features-in-machine-learning","",{"@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/detection-and-evaluation-of-bias-inducing-features-in-machine-learning/121770/",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 is cause-to-effect analysis useful for studying bias in machine learning models?","Question",{"text":75,"@type":76},"It helps break down likely causes of an undesirable outcome and connects biased behavior to underlying factors. In ML, this supports identifying how features contribute to biased predictions by analyzing root causes.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What problem does the study address regarding fairness assessment?",{"text":80,"@type":76},"Current methods often require pre-identifying sensitive features for bias assessment and may miss other bias-inducing features. The study aims for systematic identification even when such sensitive features are unknown.",{"name":82,"@type":73,"acceptedAnswer":83},"How does the proposed technique identify bias-inducing features?",{"text":84,"@type":76},"It swaps feature values and computes divergences in the distribution of model predictions using different distance functions. This reveals features whose changes materially affect predictive behavior.","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"]