Credit risk modelling
Europe’s banks can’t agree on how to fix the output floor
Some want market risk excluded, while others push for greater savings from credit modelling
Floored: Basel III rethink upsets IRB dominance
Introduction of output floor means internal ratings’ popularity takes a hit, but isn’t quite out for the count
Europe’s next chore: cleaning a floor made messy by the US
Rejection of Basel III’s output floor leaves EU with some difficult decisions to make
Graph neural networks for credit default prediction: robustness and model evaluation
The authors evaluate the robustness and performance of graph-based models in credit default prediction.
Vendor spotlight: Credit risk management solutions, 2025
Crisil has adopted a platform strategy that brings together its full suite of credit risk, analytics and regulatory capabilities
Could one-off loan losses at US regional banks become systemic?
Investors bet Zions, Western Alliance are isolated problems, but credit risk managers are nervous
Interpretable machine learning for default risk prediction in stress testing
This paper proposes a benchmark model which can be used to predict the forward-looking probability of default of a real-world credit card portfolio.
ABN Amro shifts 70% of credit risk to standardised approach
RWA increase from portfolio migration in Q3 offset by regulatory add-ons removal
Banks grapple with Fed’s double deadline on stress-test plans
Supervisor consulting simultaneously on next year’s test scenario and broader model changes
Speedy onboarding: the push for faster model approvals
Europe’s banking watchdog is planning to streamline how it authorises credit model updates. Not a moment too soon, say bankers
Generative AI brings testing times for modellers
Flagstar’s lead model validator offers some tips for safely integrating LLMs into risk models
US CRE provisions surge at Deutsche after model recalibration
Stage 2 loans drive provision hike after LGD assumptions updated
Citi’s modelled RWAs outpace standardised by record $152bn
Widening RWA output gap puts Collins floor back in spotlight
Banks seek EU supervisory green light on external credit data
GCD-developed industry standard to show pooled loss data is representative of banks’ portfolios
JPM’s reserves on undrawn loans rise 32% as Trump tariffs loom
Allowance on commitments nears $3bn as bank braces for stress among corporate borrowers
CVA risk charges spike 73% at EU banks under Basel III
Crédit Agricole leads surge, as basic approach dominates CVA capital calculations
Basel III overhaul triggers credit RWA reshuffle at EU banks
A-IRB down by a third, F-IRB more than doubles and standardised approach up by a quarter
Bank of England urged to rethink HHI concentration risk add-on
Experts think overhaul of credit risk measure should be part of PRA’s ongoing Pillar 2 review
Model risk quantification for machine learning models in credit risk
This paper analyses bank-specific model risk measurement methods with a focus on implemented model risk rating solutions for MLMs and discusses challenges faced by the validation function.
Enhancing default prediction in alternative lending: leveraging credit bureau data and machine learning
The authors apply machine learning techniques to credit bureau data and loan-specific variables to improve default prediction in the alternative lending sector.
Norinchukin trims slotting approach reliance, expands A-IRB scope
Bank’s models recover ground after Basel III curtailing