JupyterLab in Retrograde: Contextual Notifications That Highlight Fairness and Bias Issues for Data Scientists

要旨

Current algorithmic fairness tools focus on auditing completed models, neglecting the potential downstream impacts of iterative decisions about cleaning data and training machine learning models. In response, we developed Retrograde, a JupyterLab environment extension for Python that generates real-time, contextual notifications for data scientists about decisions they are making regarding protected classes, proxy variables, missing data, and demographic differences in model performance. Our novel framework uses automated code analysis to trace data provenance in JupyterLab, enabling these notifications. In a between-subjects online experiment, 51 data scientists constructed loan-decision models with Retrograde providing notifications continuously throughout the process, only at the end, or never. Retrograde's notifications successfully nudged participants to account for missing data, avoid using protected classes as predictors, minimize demographic differences in model performance, and exhibit healthy skepticism about their models.

受賞
Best Paper
著者
Galen Harrison
University of Virginia, Charlottesville, Virginia, United States
Kevin Bryson
University of Chicago, Chicago, Illinois, United States
Ahmad Emmanuel Balla. Bamba
University of Chicago, Chicago, Illinois, United States
Luca Dovichi
University of Chicago, Chicago, Illinois, United States
Aleksander Herrmann. Binion
University of Chicago, Chicago, Illinois, United States
Arthur Borem
University of Chicago, Chicago, Illinois, United States
Blase Ur
University of Chicago, Chicago, Illinois, United States
論文URL

https://doi.org/10.1145/3613904.3642755

動画

会議: CHI 2024

The ACM CHI Conference on Human Factors in Computing Systems (https://chi2024.acm.org/)

セッション: Remote Presentations: Highlight on AI

Remote Sessions
14 件の発表
2024-05-13 18:00:00
2024-05-14 02:20:00