Modelling
New model simplifies loan-loss forecasts. Some say it’s too simple
Modelling approach devised by Commerzbank quant promises to ease computational burden, but may not suit complex portfolios
Buy side turns to extreme value theory to spot tail risks
Asset managers reappraise decades-old technique to gauge downside risks amid fears of volatile 2022
SA extends reach over EU banks’ market and op risk
Regulator-devised models have been capturing a bigger chunk of RWAs through the pandemic
Does regulators’ favourite climate risk metric measure up?
FSB and Basel Committee back climate VAR, but practitioners will take some convincing
Climate risk – Special report 2021
This Risk.net special report contains a collection of articles that consider the impact rising carbon prices will have throughout the economy, discuss the challenges of modelling climate risk exposures and of integrating climate risk into risk management…
Don’t follow the models: they’re lost, too – risk managers
Risk USA: managers cite Covid, repo crisis and geopolitical risks as examples of model failures
Neural networks show fewer false positives on bad loans – study
Machine learning method edges regression techniques in linking nonlinearities among delinquent borrowers
Banks and Fed still stuck on cyber loss data sharing
OpRisk North America: Fed “trying to understand the best way to leverage cyber data”, says Curti
Regulatory feedback adds $23bn to Goldman’s RWAs
The revision to the bank's standardised RWAs brought it closer to hit the so-called Collins floor
Applying scenario analysis to climate risk
Matthew Lightwood, director, risk solutions at Conning, discusses the application of stochastic modelling with scenario analysis to quantify climate risk in a portfolio
Weather, or not: is climate risk just part of credit risk?
Practitioners divided on whether climate risk can fit into existing credit risk weights
EU banks aim to block new counterparty risk guidance
Requirement to include exposure spikes linked to swap payments within EEPE models prompts blowback
APG hires in-house weatherman to interpret climate data
Europe’s wettest summer in a century prompts asset managers to calculate flood risk for real estate
NLP and transformer models for credit risk
News feeds are factored into models to predict credit events
Building forward-looking scenarios: why you’re doing it wrong
Rick Bookstaber and colleagues describe a process for constructing effective scenarios
Show your workings: lenders push to demystify AI models
Machine learning could help with loan decisions – but only if banks can explain how it works. And that’s not easy
Model change cuts Barclays’ VAR 21% in H1
Reducing historical lookback period from two years to one shaves £5m off bank’s average VAR
Podcast: Claudio Albanese on how bad models survive
Darwin’s theory of natural selection could help quants detect flawed models and strategies
Goldman tackles climate risk controls
Lender joins other banks in translating physical and transition threats into controls framework
Risk managers urge consolidation of climate scenarios
Converging financial and corporate scenarios would provide better data for stress-testing
Nomura understated VAR capital charges by 13% in H2 2020
VAR RWAs should have been ¥122 billion higher than originally stated at end-December
How algos are helping inflation-wary investors
Buy-siders look to machine learning for clues on the effect of rising prices on portfolios
Deep XVAs and the promise of super-fast pricing
Intelligent robots can value complex derivatives in minutes rather than hours
Banks fear Fed crackdown on AI models
Dealers say agencies’ request for info could prompt new rules that stifle model innovation