The safeguards map / 2.1 Tester-run
Intersectional Fairness (ISF)
Drafted with AI
Drafted with AI from the cited sources under the direction of UnGovr staff. UnGovr holds editorial responsibility for this page. How this site is made
An archived Python library for detecting and mitigating bias that combinations of several protected attributes cause in machine-learning models.
Where it sits
2.1 Tester-run (primary): Detects bias in machine-learning models that combinations of multiple protected attributes cause, as a library a developer runs from Python and notebooks.
Intersectional Fairness (ISF) is a bias detection and mitigation technology for intersectional bias
captured
The `examples` directory contains a diverse collection of jupyter notebooks
captured
Facts
- Concern
- safety
- Names the law
- no
- Subject
- AI model
- Used by
- those who make it
- Runs
- by hand
- Tests
- model behavior
Handoffs
None recorded.
Listed, not drawn: it is archived.
Collector's note
Archived, with its code folded into AI Fairness 360 (already in the map). Only its bias detection function is placed.
Every quote is verbatim from a stored capture of the page linked under it. Placement is our reading of the product's own documentation; no publisher has reviewed or endorsed it. Rows CC BY 4.0. Names, marks and logos belong to their owners; logos identify each product and are not part of the dataset.