Model risk
US watchdogs seek to govern bank AML systems as models
Banks fear prudential agencies’ move could hamper their own ability to fight financial crime
Model reviews imposed capital charges on top EU banks in Q4
Societe Generale incurred a -36bp hit to its CET1 ratio due to Trim
Statistical properties of the population stability index
This paper aims to fill a gap in the literature by providing statistical properties of the population stability index (PSI) and some recommendations on its use.
Parallel lines: EU begins fight over Basel output floor
Leaked plan to exclude buffers from floor would please EU banks, could anger Basel and US
Fed will start FRTB model approvals for US banks in 2021
Senior official says banks should now be deciding desk structure and readying backtests
Quants tout alternative carry trades for the ‘new normal’
Low rates and flatlining yield curves leave investors seeking carry in swaps and swaptions
Level 3 assets fell at top US banks in Q2
Mark-to-model instruments disclosed by banks over $100 billion in size contracted 4%
Hypothetical yield curve scenarios for credit stress testing
In this paper, we discuss a set of hypothetical yield curve shift scenarios generated by applying extreme value distributions and a shaping procedure. These statistically derived hypothetical stress scenarios could be susceptible to model risk, leading…
Fix to Fed stress test snafu lowers two banks’ capital charges
Goldman, Morgan Stanley see stress capital buffer cuts
A k-means++-improved radial basis function neural network model for corporate financial crisis early warning: an empirical model validation for Chinese listed companies
This paper aims to simplify the early warning model for financial crises by collecting and analyzing the financial data of Chinese special treatment (ST) companies, normally listed companies and cancel special treatment (CST) companies.
Big buy-side firms seek better model risk disclosures
Working group building standardised disclosure doc for managers and vendors
Top banks defer €1.6bn of profits on hard-to-value trades in H1
BNP Paribas set aside €532 million alone in H1
Benchmarking operational risk stress testing models
This paper outlines several approaches to benchmarking operational loss projections under stressed scenarios using both accounting metrics and historical loss experience.
Why investors are stuck with flawed VAR models
Buy-side risk survey: VAR wasn’t much use in March, but it is ingrained in the industry
Valuation risks fell at UBS in Q2
Swiss lender is sitting on $8.1 billion of Level 3 assets
Mark-to-model assets spiked at eurozone banks in Q1
Level 3 derivatives assets increased 52% quarter-on-quarter
An emergent taxonomy for operational risk: capturing the wisdom of crowds
In this paper, the author takes a data-driven approach and combines the individual active taxonomies of sixty large financial institutions (fifty-eight for construction and two for validation) to create a coherent new reference taxonomy: the ORX…
A positive response to negative oil prices
Overhauling pricing models could reap rewards even if prices don’t cross zero again
Rewards for failure: the ECB’s topsy-turvy market risk relief
Eurozone banks with better models are least able to offset Covid-driven rise in backtesting multiplier
Bachelier – a strange new world for oil options
Model tuned to negative prices has implications for pricing, margining and delta hedging
Covid-19 – Developing resiliency to ensure business continuity
Covid-19 has forced firms worldwide to question how they plan for, build and maintain resiliency to ensure business continuity. With operational and cyber risk departments now firmly concentrating on pandemic action plans and emerging risks, this webinar…
Machine learning in fraud analytics to combat financial crime – Getting it right
Risk and compliance professionals gathered for a Risk.net webinar in association with NICE Actimize to consider the challenges and opportunities of successfully harnessing artificial intelligence in the fight against financial criminals
Machine learning in fraud analytics – Getting it right
Over the past couple of years, financial institutions have made significant achievements in the fight against fraud by embracing machine learning analytics and advanced artificial intelligence
As Covid snaps credit models, lenders turn to stress-testing
Banks enlist scenario analysis to bolster creaking default models