@kldivergence : Evaluating subgroup disparities in ML shouldn't only be a "fairness" thing. It should be ML/data science best practice in general. If your model performs poorly for some identifiable subgroup, you should probably go fix that, just in the interest of making a better model. • TwiCopy

Kristian Lum

@kldivergence

+ Follow

Research Scientist at Google DeepMind | @FAccTConference OG | Past Twitter META, @hrdag & UPenn, UChicago faculty |

ID: 32513057

calendar_today17-04-2009 18:32:57

6,6K Tweet

22,22K Followers

1,1K Following

Kristian Lum

@kldivergence

3 years ago

Evaluating subgroup disparities in ML shouldn't only be a "fairness" thing. It should be ML/data science best practice in general. If your model performs poorly for some identifiable subgroup, you should probably go fix that, just in the interest of making a better model.

thumb_up_off_alt268

chat_bubble_outline14

repeat44

shareShare