A Distributionally Robust Optimisation Approach to Fair Credit Scoring

This paper presents a distributionally robust optimization (DRO) framework for fair credit scoring that addresses model performance disparities across demographic groups while maintaining predictive accuracy. The approach uses uncertainty sets to hedge against distributional shifts and fairness violations, making it relevant for financial institutions navigating fairness constraints and regulatory compliance in lending decisions.

This paper presents a distributionally robust optimization (DRO) framework for fair credit scoring that addresses model performance disparities across demographic groups while maintaining predictive accuracy. The approach uses uncertainty sets to hedge against distributional shifts and fairness violations, making it relevant for financial institutions navigating fairness constraints and regulatory compliance in lending decisions.

Legal AI must preserve privilege, satisfy ethics rules, and keep client data within a defensible perimeter. QuettaMinds helps law firms and legal departments deploy AI that is structurally compliant, not just policy-compliant.