Machine-learning bias often stems from unrepresentative training data
Categorization
- corroborated: 3 independent passages support this claim
- XREF: connects to: Machine learning systems are not inherently fair or just by default; Even massive, comprehensive text datasets reflect biases present in the real world; ProPublica tested COMPAS recidivism predictions against actual reoffense outcomes for bias (+11 more)
Related
- Machine learning systems are not inherently fair or just by default (similarity 0.82)
- Machine learning models encode the historical base rates present in their training data (similarity 0.80)
- ProPublica tested COMPAS recidivism predictions against actual reoffense outcomes for bias (similarity 0.80)