We introduce Fairlearn, an open source toolkit that empowers data scientists and developers to assess and improve the fairness of their AI systems. Fairlearn has two components: an interactive visualization dashboard and unfairness mitigation algorithms. These components are designed to help with navigating trade-offs between fairness and model performance. We emphasize that prioritizing fairness in AI systems is a sociotechnical challenge. Because there are many complex sources of unfairness\u2014some societal and some technical\u2014it is not possible to fully \u201cdebias\u201d a system or to guarantee fairness; the goal is to mitigate fairness-related harms as much as possible. As Fairlearn grows to include additional fairness metrics, unfairness mitigation algorithms, and visualization capabilities, we hope that it will be shaped by a diverse community of stakeholders, ranging from data scientists, developers, and business decision makers to the people whose lives may be affected by the predictions of AI systems.<\/p>\n","protected":false},"excerpt":{"rendered":"
We introduce Fairlearn, an open source toolkit that empowers data scientists and developers to assess and improve the fairness of their AI systems. Fairlearn has two components: an interactive visualization dashboard and unfairness mitigation algorithms. These components are designed to help with navigating trade-offs between fairness and model performance. We emphasize that prioritizing fairness in […]<\/p>\n","protected":false},"featured_media":660288,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"footnotes":""},"msr-content-type":[3],"msr-research-highlight":[],"research-area":[13556],"msr-publication-type":[193718],"msr-product-type":[],"msr-focus-area":[],"msr-platform":[],"msr-download-source":[],"msr-locale":[268875],"msr-field-of-study":[],"msr-conference":[],"msr-journal":[],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-660249","msr-research-item","type-msr-research-item","status-publish","has-post-thumbnail","hentry","msr-research-area-artificial-intelligence","msr-locale-en_us"],"msr_publishername":"","msr_edition":"","msr_affiliation":"","msr_published_date":"2020-5-18","msr_host":"","msr_duration":"","msr_version":"","msr_speaker":"","msr_other_contributors":"","msr_booktitle":"","msr_pages_string":"","msr_chapter":"","msr_isbn":"","msr_journal":"","msr_volume":"","msr_number":"MSR-TR-2020-32","msr_editors":"","msr_series":"","msr_issue":"","msr_organization":"Microsoft","msr_how_published":"","msr_notes":"","msr_highlight_text":"","msr_release_tracker_id":"","msr_original_fields_of_study":"","msr_download_urls":"","msr_external_url":"","msr_secondary_video_url":"","msr_longbiography":"","msr_microsoftintellectualproperty":1,"msr_main_download":"","msr_publicationurl":"","msr_doi":"","msr_publication_uploader":[{"type":"file","viewUrl":"https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2020\/05\/Fairlearn_WhitePaper-2020-09-22.pdf","id":"694197","title":"fairlearn_whitepaper-2020-09-22","label_id":"243109","label":0}],"msr_related_uploader":"","msr_attachments":[{"id":694197,"url":"https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2020\/09\/Fairlearn_WhitePaper-2020-09-22.pdf"},{"id":660282,"url":"https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2020\/05\/Fairlearn_whitepaper.pdf"}],"msr-author-ordering":[{"type":"user_nicename","value":"Sarah Bird","user_id":33684,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Sarah Bird"},{"type":"user_nicename","value":"Miro Dud\u00edk","user_id":32867,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Miro Dud\u00edk"},{"type":"text","value":"Richard Edgar","user_id":0,"rest_url":false},{"type":"text","value":"Brandon Horn","user_id":0,"rest_url":false},{"type":"text","value":"Roman Lutz","user_id":0,"rest_url":false},{"type":"text","value":"Vanessa Milan","user_id":0,"rest_url":false},{"type":"text","value":"Mehrnoosh Sameki","user_id":0,"rest_url":false},{"type":"user_nicename","value":"Hanna Wallach","user_id":34779,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Hanna Wallach"},{"type":"text","value":"Kathleen Walker","user_id":0,"rest_url":false}],"msr_impact_theme":[],"msr_research_lab":[],"msr_event":[],"msr_group":[372368],"msr_project":[],"publication":[],"video":[],"download":[],"msr_publication_type":"techreport","_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/660249"}],"collection":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item"}],"about":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-research-item"}],"version-history":[{"count":2,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/660249\/revisions"}],"predecessor-version":[{"id":694185,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/660249\/revisions\/694185"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media\/660288"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=660249"}],"wp:term":[{"taxonomy":"msr-content-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-content-type?post=660249"},{"taxonomy":"msr-research-highlight","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-highlight?post=660249"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=660249"},{"taxonomy":"msr-publication-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-type?post=660249"},{"taxonomy":"msr-product-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-product-type?post=660249"},{"taxonomy":"msr-focus-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-focus-area?post=660249"},{"taxonomy":"msr-platform","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-platform?post=660249"},{"taxonomy":"msr-download-source","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-download-source?post=660249"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=660249"},{"taxonomy":"msr-field-of-study","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-field-of-study?post=660249"},{"taxonomy":"msr-conference","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-conference?post=660249"},{"taxonomy":"msr-journal","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-journal?post=660249"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=660249"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=660249"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}