IBI Score
6.9
out of 10
Severity4_grave
Frequencyfrequent
Scope groups4
Detection difficulty2
🇫🇷 Définition (FR)
Utilisation d'une seule métrique d'évaluation masquant les compromis et les biais.
🇬🇧 Definition (EN)
Use of a single evaluation metric masking trade-offs and biases.
TriAxis Taxonomy
Structural Classification
O
Origin
O2
Computational & Statistical
L
Lifecycle
L6
Evaluation
S
Specific
S17
Measurement error bias
💡
Concrete Example
Une équipe optimise uniquement la précision et rate les biais de rappel sur les minorités.
📊 Detection Metrics
Demographic Parity DifferenceDisparate Impact RatioEqualized Odds Difference
⚙ Alert Thresholds
Disparate Impact Ratio0.8
Equalized Odds Difference0.1
Demographic Parity Difference0.1
📚 Sources & Scientific References
- •
- •A Systematic Analysis of Performance Measures for Classification TasksSokolova, M., Lapalme, G. (2009)
- •Fairness and Abstraction in Sociotechnical SystemsSelbst, A. D., boyd, d., Friedler, S. A., Venkatasubramanian, S., Vertesi, J. (2019)
🛡 Impact & Mitigation
🎯 Vulnerable groups impacted
No specific groups.
🛠 Mitigation methodologies
- EQ_ODDS : Equalized Odds
- DEMO_PARITY : Demographic Parity
- CALIBRATION : Calibration by Group
- AUDIT_TIERS : Third-party Audit
🏢 Sectors concerned
Finance & Banking (Risk: /5)Healthcare & Medicine (Risk: /5)
⚖ Applicable regulations
🌍 International
- •ISO_42001 : ISO/IEC 42001:2023
- •UNESCO_2021 : UNESCO - Recommandation sur l'éthique de l'IA
- •OECD_AI_PRINCIPLES : OCDE - Principes IA
- •COE_AI_CONVENTION_INT : Conseil de l'Europe - Convention IA
📋 Metadata
Contributor
Mohamadou SIDIBE
Institution
AI BIAIS INITIATIVE
Version
1
Created on
October 14, 2026
Updated on
November 4, 2026
UUID
77f31509-8027-4506-9b21-cb6253115128
Explore other biases
250 documented biases, classified by the TriAxis taxonomy.