Assessing and Addressing Algorithmic Bias - But Before We Get There
Abstract
Algorithmic and data bias are gaining attention as a pressing issue in popular press - and rightly so. However, beyond these calls to action, standard processes and tools for practitioners do not readily exist to assess and address unfair algorithmic and data biases. The literature is relatively scattered and the needed interdisciplinary approach means that very different communities are working on the topic. We here provide a number of challenges encountered in assessing and addressing algorithmic and data bias in practice. We describe an early approach that attempts to translate the literature into processes for (production) teams wanting to assess both intended data and algorithm characteristics and unintended, unfair biases.
Cite
@article{arxiv.1809.03332,
title = {Assessing and Addressing Algorithmic Bias - But Before We Get There},
author = {Jean Garcia-Gathright and Aaron Springer and Henriette Cramer},
journal= {arXiv preprint arXiv:1809.03332},
year = {2018}
}
Comments
The version submitted here for FATREC 2018 is a condensed version of our publication which originally appeared in the 2018 AAAI Spring Symposium Series under the "Design of the User Experience for Artificial Intelligence" track. The original publication can be found here: https://www.aaai.org/ocs/index.php/SSS/SSS18/paper/view/17542/15470