Credit risk modelling
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.
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
Basel III prompts Scandi banks to redraw credit risk
Danske, Handelsbanken and Nykredit scale back A-IRB under new rules
Wait in the Q: US banks hold back on tariff-related provisions
Lack of data on supply chain vulnerabilities creates challenges for early CECL adjustments
Amid tariff turmoil, banks warned not to fudge IFRS 9 overlays
Flip-flopping US policies challenge loan loss provisioning models; EU regulators take watching brief
Rabobank jacks up climate risk overlays to loan provisions
Allowances top-up for chronic extreme weather increases more than sixfold
Basel III spurs €62bn credit RWA reshuffle at Rabobank
Bank switched corporate portfolios from A- to F-IRB on eve of reforms’ January 1 go-live
Credit loss database reveals holes in Basel’s IRB formula
Researcher has used two decades of data to propose improved internal model methodology
Shaking things up: geopolitics and the euro credit risk measure
Gravitational model offers novel way of assessing national and regional risks in new world order
How a serverless risk engine transformed a digital bank
Migrating to the cloud permitted scalability, faster model updates and a better team structure
IRB reliance peaks at over 90% for some lenders ahead of Basel III shift
As reforms loom, IRB usage spans from marginal to near-total among European banks