156 | Visualizing Fairness in Machine Learning with Yongsu Ahn and Alex Cabrera
Data Stories
00:00
Machine Learning
The type of fairness you talk about iss mostly related to not being discriminatory, or not using features that have nothing to do with the essential decision you're making. So it's about combating discrimination. It's a little bit more complicated. Just the complex relationships between the variables ends up that you can actually recreate the bioces even having no idea the augar them,. Not being aware of these protected attributes. But just to understand hat. A fair valuation is one that only takes the features into account that you're supposed to take into account.
Transcript
Play full episode
