Changing data properties and missing data
See the effect of a shift in group B's distribution and unequal missing data on fairness.
العربيةThe idea
Sweeps the shift and reports accuracy, disparate impact and equal opportunity difference.
Data description
Synthetic data generated in your browser from stated distributions; no real personal data.
Suggested next experiment
Scientific sources for this experiment
- A Framework for Understanding Sources of Harm throughout the ML Life Cycle (arXiv:1901.10002)H. Suresh, J. Guttag (2019) — Paper
- A Survey on Bias and Fairness in Machine Learning (arXiv:1908.09635)N. Mehrabi et al. (2019) — Paper
