Dec 11, 2014 · We propose a test for disparate impact based on analyzing the information leakage of the protected class from the other data attributes.

We propose a test for disparate impact based on how well the protected class can be predicted from the other attributes.

Aug 10, 2015 · In U.S. law, unintentional bias is encoded via disparate impact, which occurs when a selection process has widely different outcomes for ...

Aug 10, 2015 · Our procedure for detecting disparate impact goes through an actual classification algorithm. As we show in our experi- ments, a better ...

This paper proposes a method to eliminate bias from predictive models by removing all information regarding protected variables from the data.

Feldman, M.; Friedler, S.; Moeller, J.; Scheidegger, C.; Venkatasubramanian, S. (2015). "Certifying and Removing Disparate Impact." Proceedings of the 21st ACM ...

It is Bob's job to verify that on the data D, Alice's algorithm A is not liable for a claim of disparate impact. ○ Assumptions: ○ Bob has no access to algorithm ...

In U.S. law, unintentional bias is encoded via disparate impact, which occurs when a selection process has widely different outcomes for different groups, even ...

In U.S. law, the notion of bias is typically encoded through the idea of disparate impact: namely, that a process (hiring, selection, etc) that on the surface ...

In U.S. law, unintentional bias is encoded via disparate impact, which occurs when a selection process has widely different outcomes for different groups, even ...