Fairness Under Unawareness: Assessing Disparity When Protected Class Is Unobserved

Assessing the fairness of a decision making system with respect to a protected class, such as gender or race, is challenging when class membership labels are unavailable. Proxies, such as surname and geolocation for race, are sometimes used to impute these missing labels for compliance assessments. In this paper, the authors decompose the biases arising from this and propose an alternative.

Download here

Chosen by

Reuben Binns

Theme

Accountability

Related files

Download here

Sign up to our Newsletter

 We would love to stay in touch.

Our newsletters and updates let you know what we’ve been up to, what’s in the pipeline, and give you the chance to sign up for our events.

 You can unsubscribe at anytime by clicking the link at the bottom of our emails or by emailing dataprotection@ifow.org. Read our full privacy policy including how your information will be stored by clicking the link below.