no code implementations • 5 Feb 2023 • Brent Mittelstadt, Sandra Wachter, Chris Russell
Many current fairness measures suffer from both fairness and performance degradation, or "levelling down," where fairness is achieved by making every group worse off, or by bringing better performing groups down to the level of the worst off.
no code implementations • 2 May 2022 • Sandra Wachter
Artificial Intelligence (AI) is increasingly used to make important decisions about people.
1 code implementation • 12 May 2020 • Sandra Wachter, Brent Mittelstadt, Chris Russell
Through this proposal for procedural regularity in the identification and assessment of automated discrimination, we clarify how to build considerations of fairness into automated systems as far as possible while still respecting and enabling the contextual approach to judicial interpretation practiced under EU non-discrimination law.
no code implementations • 4 Nov 2018 • Brent Mittelstadt, Chris Russell, Sandra Wachter
Recent work on interpretability in machine learning and AI has focused on the building of simplified models that approximate the true criteria used to make decisions.
5 code implementations • 1 Nov 2017 • Sandra Wachter, Brent Mittelstadt, Chris Russell
We suggest data controllers should offer a particular type of explanation, unconditional counterfactual explanations, to support these three aims.