Differential performance across populations

https://taxonomy.eticas.ai/risk/performance-equity

Maturity: emerging

The AI system performs systematically worse for some demographic groups than others — through higher error rates, lower accuracy, or reduced reliability — leading to unequal quality of service even when access is the same.

This category is emerging. It has not yet been validated through established assessment methods.

Also known as: Group-wise error rate · Performance equity across populations

System type: ADM and LLM systems
Lifecycle stages: Pre Processing, In Processing, Post Processing

Mappings to external frameworks

Standards & frameworks

Framework Reference
AIUC-1 — AI Underwriting Company Standard Prevent customer-defined high-risk outputs
NIST AI Risk Management Framework (AI 100-1) Fair – with Harmful Bias Managed
NIST AI Risk Management Framework (AI 100-1) MEASURE 2.11: Fairness and bias – as identified in the MAP function – are evaluated and results are documented.

Taxonomies & vocabularies

Framework Reference
MIT AI Risk Repository Unequal performance across groups

Source: HRA project taxonomy