Correlation between outcomes and race, gender, etc. is NOT bias per se. And yet that's what almost all claims of discrimination by machine-learned models are based on.
-
There are plenty of valid claims that do not reduce to correlation of outcomes. This study points to higher false positive rates of recidivist risk rates for black individuals https://www.propublica.org/article/how-we-analyzed-the-compas-recidivism-algorithm/ …. Obviously this is just one study but it’s not as simple as you make it.
Odd example. Correlation between race and recidivism is exactly what's behind this (long debunked) study.
-
-
I’m trying to get at - assume blacks have higher rates of recidivism than whites by 2x. If model predicts 3x rate for blacks, isn’t that bias? Shouldn’t it predict 2x? I know it’s not that simple but I imagine there are other cases like this because of poor data/feature selection
Uusi keskustelu -
-
-
I can’t speak to the validity of the study so apologies if it’s already been debunked.
Kiitos. Käytämme tätä aikajanasi parantamiseen. KumoaKumoa
-
Lataaminen näyttää kestävän hetken.
Twitter saattaa olla ruuhkautunut tai ongelma on muuten hetkellinen. Yritä uudelleen tai käy Twitterin tilasivulla saadaksesi lisätietoja.