www-ai.cs.tu-dortmund.de/LEHRE/SEMINARE/WS2021/TrustworthyAIMachineLearning/literature/zafar2019.pdf
domains. Examples of such domains include credit approval (FICO, 2017), criminal risk assessment (Perry, 2013), hir-
. A preliminary version of this work appeared in Zafar et al. (2017a,b).
. Open-source code [...] (Bhandari, 2016), governments (Podesta et al., 2014; Muñoz et al., 2016), and researchers (Sweeney, 2013) alike have raised concerns about the unfairness of these algo- rithmic decision systems towards people [...] vies et al., 2017; Hardt et al., 2016; Feldman et al., 2015; Zafar et al., 2017b,a; Zemel et al., 2013; Dwork et al., 2012). In doing so, they have have measured the (un)fairness of a decision making process …
