Model validation
The bank quant who wants to stop gen AI hallucinating
Wells Fargo model risk chief thinks he has found a way to validate large language models
Will generative AI crack the code for bank tech teams?
Banks could roll out tools to help translate old – or write new – code within months
Can CRE credit risk models cope with hybrid working?
As US office use changes, modellers deploy judgement overlays and alternative data to keep up
Climate risk overlays unnerve model-validation teams
Risk Live: Model risk managers fear they lack the data or skills to properly test expert judgement
Party’s over as more banks drop internal models for market risk
At least three systemic banks in Europe intend to ditch IMA for capital requirements
A new automated model validation tool for financial institutions
The authors put forward a novel automated validation tool, based on US Federal Reserve and Office of the Comptroller of the Currency regulatory guidance, which is used to to validate predictive models for financial organizations.
BoE model risk rule may drive real-time monitoring of AI
New rule requires banks to rerun performance tests on models that recalibrate dynamically
Banks’ internal watchdogs bark back at ChatGPT
Generative AI has plenty of uses in finance, but banks must first overcome compliance headaches
EU rulemakers lean towards Simm validation for dealers only
Council supports EBA proposal to narrow scope of rules, while parliament takes a tougher line
EU banks balk at new market risk models back test
EBA proposals introduce additional expected shortfall back test for market capital risk models under FRTB
New BoE rules could force banks to cull multiplying models
Risk Live: Model risk management to become more labour-intensive, as model definition is broadened
A modified hybrid feature-selection method based on a filter and wrapper approach for credit risk forecasting
This paper proposes the chi-squared with recursive feature elimination method: a means of feature-selection which aims to improve classification performance using fewer features.
The validation of different systemic risk measurement models
The authors incorporate a capital buffer to the DebtRank model and use data from China's banking industry to compare the proposed model with others.
US falls behind in race to match Europe’s FRTB launch date
Recent US bank failures could jeopardise planned January 2025 start date for Basel III
Performance validation of representative sample-balancing methods in loan credit-scoring scenarios
The authors validate 12 of the most representative sample-balancing methods used for credit-scoring models, finding that a combined SMOTE and Editor Nearest Neighbor method is optimal.
Bot’s job? Quants question AI’s model validation powers
But supervisors cautiously welcome next-gen model risk management
Quantification of model risk with an application to probability of default estimation and stress testing for a large corporate portfolio
This paper discusses the building of obligor-level rather than segment-level hazard rate corporate probability of default models for stress testing.
Machine learning models: the validation challenge
Machine learning models are seeing increasing demand across the capital markets spectrum. But how can firms improve their chances of gaining internal and regulatory approval for these type of models?
PRA’s pot shots threaten Simm’s global ubiquity
UK regulator’s push to improve model governance could tip non-cleared derivatives market into chaos
General bounds on the area under the receiver operating characteristic curve and other performance measures when only a single sensitivity and specificity point is known
Using a single true positive - true negative pair, the author shows how to calculate the area under a ROC curve.
Covid chaos spurs on search for model risk aggregation
Many models failed in pandemic, but analysing them in clusters easier than whole-bank view