The safeguards map / 2.1 Tester-run
AI Fairness 360 (AIF360)
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
A Python and R library with metrics that test datasets and machine learning models for bias, and algorithms that mitigate it.
Where it sits
2.1 Tester-run (primary): Measures bias in datasets and machine learning models with a set of fairness metrics that a developer runs and reads.
a comprehensive set of metrics for datasets and models to test for biases
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. A mapped entry with no handoff is here for its foundation home.
Collector's note
Concern is safety because bias is a way a system can harm people with no attacker involved. The library also ships mitigation algorithms; only the testing function is mapped.
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.