Tag
This paper audits confidence-based label filtering in automated credit default prediction, revealing income-conditional recall disparities and showing that blinding models to sensitive attributes does not eliminate fairness gaps when proxies and institutional biases persist.
This paper systematically evaluates reject inference methods in credit scoring and identifies a failure mode where accuracy improves while recall collapses, creating an illusion of improvement while rejection quality deteriorates. It proposes a controlled exploration strategy that breaks the feedback loop and shows that even minimal exploration rates are sufficient to diagnose the problem.
This paper develops a framework to grade the capability to infer in data-driven systems under the European AI Act, using credit scoring as a case study to illustrate where inference occurs and where regulatory clarity is needed.
This survey examines computational nondeterminism in financial AI systems, covering tabular models, graph networks, and LLM-based workflows, and proposes a layered evaluation framework for auditability.