A test that trains a model to predict a protected attribute from a system's features; features that predict it strongly are flagged as proxies to justify or remove, and the result is recorded in the data card. It finds proxy variables before an outcome metric shows their effect.
- Developed in
- ch. 16, Fairness and explainability in the stack
ch. 05, Pattern: Fairness Eval Suite - Chapters
- ch. 05, Patterns · ch. 16, Fairness & XAI
- Source
- Defined by this Body of Knowledge: the section it is developed in is the source
Where it is used
2 chapters of the Body of Knowledge use the term. Each link opens the first section that does.
- 05 · Patterns Pattern: Fairness Eval Suite 1 mention
- 16 · Fairness & XAI Where bias enters the lifecycle 5 mentions
Related terms
Sources
No external source: the term is coined or used in a specific sense by this Body of Knowledge, and the section linked under "Developed in" is its source.
Definitions of legal terms paraphrase the cited text, which governs. Dated statements are as of .