"Fairness Through Awareness" makes the observation that sometimes, in
order to be fair, it is important to make use of sensitive information
while carrying out the classification task. This may be a little
counterintuitive: The instinct might be to hide information that could
be the basis of discrimination.
-- Cynthia Dwork, Microsoft Research, referring to her own paper,
in an interview by
Claire Cain Miller, "Algorithms and Bias: Q. and A. With Cynthia Dwork"
New York Times (Aug. 10, 2015)
http://www.nytimes.com/2015/08/11/upshot/algorithms-and-bias-q-and-a-with-cynthia-dwork.html
Fairness means that similar people are treated similarly. A true
understanding of who should be considered similar for a particular
classification task requires knowledge of sensitive attributes, and
removing those attributes from consideration can introduce unfairness
and harm utility.
-- Cynthia Dwork, Microsoft Research, referring to her own paper,
http://arxiv.org/abs/1104.3913 in an interview by
Claire Cain Miller, "Algorithms and Bias: Q. and A. With Cynthia Dwork"
New York Times (Aug. 10, 2015)
http://www.nytimes.com/2015/08/11/upshot/algorithms-and-bias-q-and-a-with-cynthia-dwork.html