João Paulo Vieira Costa

Banco do Brasil

João Paulo Vieira Costa is a Ph.D. candidate at the University of Brasília (UnB) and a professional in the internal controls department of a major Brazilian financial institution. His research encompasses artificial intelligence models, specifically document understanding, alongside credit risk modeling and IFRS 9 compliance. His work in the financial sector applies survival analysis and ensemble methods to estimate lifetime probability of default (PD). He also investigates dynamic credit risk characterization for fintechs and the impact of central bank interventions on non-performing loans. Currently, his work focuses on integrating multimodal architectures and emerging AI technologies into corporate governance

Articles by João Paulo Vieira Costa

Original research

Beyond mirror validation: the cost of ineffective challenge in model risk management

The authors demonstrate that the practice of confirming a developer’s model is correctly reimplemented and discrimination metrics are acceptable while leaving calibration under changing conditions unchallenged fails to detect calibration degradation.

27 Sep 2026

You need to sign in to use this feature. If you don’t have a Risk.net account, please register for a trial.

You are currently on corporate access.

To use this feature you will need an individual account. If you have one already please sign in.

Alternatively you can request an individual account here