Analysing documented failure cases
Link real, published failures to the principle that failed and the metric that would have caught it.
العربيةThe idea
Four cases with sources; choose the principle and compare with the analysis.
Data description
Summaries of cited published sources.
Suggested next experiment
Scientific sources for this experiment
- Machine BiasJ. Angwin, J. Larson, S. Mattu, L. Kirchner (ProPublica) (2016) — Documented case
- Gender Shades: Intersectional Accuracy Disparities in Commercial Gender Classification (PMLR 81:77–91)J. Buolamwini, T. Gebru (2018) — Paper
- Simple Demographics Often Identify People UniquelyL. Sweeney (2000) — Paper
