Dear ML reading group,
This week we will have Deborah presenting the paper *Not So Fair: The Impact of Presumably Fair Machine Learning Models* (paper here https://dl.acm.org/doi/10.1145/3600211.3604699). The reading group will take place on *Wednesday at 2:30pm *as usual, and this time we will host physically at *room 0.01 of building E1.7 @ UdS*. For those attending remotely, you can find the Zoom link in the reading group spreadsheet https://docs.google.com/spreadsheets/d/1vtgEezBqS4d_ACPt-emK2NT52x7nofX9jxgH1N04MQE/edit?usp=sharing.
*Abstract:*
When bias mitigation methods are applied to make fairer machine learning models in fairness-related classification settings, there is an assumption that the disadvantaged group should be better off than if no mitigation method was applied. However, this is a potentially dangerous assumption because a “fair” model outcome does not automatically imply a positive impact for a disadvantaged individual—they could still be negatively impacted. Modeling and accounting for those impacts is key to ensure that mitigated models are not unintentionally harming individuals; we investigate if mitigated models can still negatively impact disadvantaged individuals and what conditions affect those impacts in a loan repayment example. Our results show that most mitigated models negatively impact disadvantaged group members in comparison to the unmitigated models. The domain-dependent impacts of model outcomes should help drive future bias mitigation method development.
Cheers, Adrián