{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/on-the-impossibility-of-fairness","title":"On the (im)possibility of fairness","arxiv_id":"1609.07236","date":"2016-09-23","proceeding":null,"authors":["Sorelle A. Friedler","Carlos Scheidegger","Suresh Venkatasubramanian"],"abstract":"What does it mean for an algorithm to be fair? Different papers use different\nnotions of algorithmic fairness, and although these appear internally\nconsistent, they also seem mutually incompatible. We present a mathematical\nsetting in which the distinctions in previous papers can be made formal. In\naddition to characterizing the spaces of inputs (the \"observed\" space) and\noutputs (the \"decision\" space), we introduce the notion of a construct space: a\nspace that captures unobservable, but meaningful variables for the prediction.\n  We show that in order to prove desirable properties of the entire\ndecision-making process, different mechanisms for fairness require different\nassumptions about the nature of the mapping from construct space to decision\nspace. The results in this paper imply that future treatments of algorithmic\nfairness should more explicitly state assumptions about the relationship\nbetween constructs and observations.","url_abs":"http://arxiv.org/abs/1609.07236v1","url_pdf":"http://arxiv.org/pdf/1609.07236v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"on-the-impossibility-of-fairness","repo_url":"https://github.com/cteicher-m/loanBiases","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"on-the-impossibility-of-fairness","repo_url":"https://github.com/yclavinas/ai_big_data_quantum_compution","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"GPL-3.0"}}],"tasks":[{"task_slug":"decision-making","task_name":"Decision Making"},{"task_slug":"fairness","task_name":"Fairness"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1609.07236","atlas_url":"https://app.syntology.ai/?focus=1609.07236","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}