{"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/iterative-orthogonal-feature-projection-for","title":"Iterative Orthogonal Feature Projection for Diagnosing Bias in Black-Box Models","arxiv_id":"1611.04967","date":"2016-11-15","proceeding":null,"authors":["Julius Adebayo","Lalana Kagal"],"abstract":"Predictive models are increasingly deployed for the purpose of determining\naccess to services such as credit, insurance, and employment. Despite potential\ngains in productivity and efficiency, several potential problems have yet to be\naddressed, particularly the potential for unintentional discrimination. We\npresent an iterative procedure, based on orthogonal projection of input\nattributes, for enabling interpretability of black-box predictive models.\nThrough our iterative procedure, one can quantify the relative dependence of a\nblack-box model on its input attributes.The relative significance of the inputs\nto a predictive model can then be used to assess the fairness (or\ndiscriminatory extent) of such a model.","url_abs":"http://arxiv.org/abs/1611.04967v1","url_pdf":"http://arxiv.org/pdf/1611.04967v1.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":"iterative-orthogonal-feature-projection-for","repo_url":"https://github.com/yevgeni-integrate-ai/vfae","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"fairness","task_name":"Fairness"}],"methods":[{"method_slug":"interpretability","method_name":"Interpretability"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1611.04967","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}