Historical data
Can machine learning help predict recessions? Not really
Artificial intelligence models stumble on noisy data and lack of interpretability
FRTB managers face hard facts about risk factors
There are ways to reduce the capital charges caused by NMRFs, but they come at a price
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
Optimal allocation to cryptocurrencies in diversified portfolios
Asset allocation methods assign positive weights to cryptos in diversified portfolios
Vol pushed HSBC’s modelled market risk up 37% in Q3
Erratic markets in Europe and Asia blamed for $6.4bn increase led by VAR and SVAR-based charges
As interest rates surge, bankers fret over last year’s models
IRRBB modellers trying to predict client behaviour have little relevant data to fall back on
Banks shock commodities by 1,000% in stress-test rethink
Energy price spikes force clearing firms to consider extreme or even ‘implausible’ scenarios
Capital One changed SVAR window 24 times in Q1
Since 2020, the lender updated its chosen stress period dozens of times each quarter, far more frequently than peers
Danske, Deutsche and PNC pin SVAR to Covid-19
Most global banks continue to use the global financial crisis to stress-test their portfolios
JP Morgan leads US banks on surging VAR capital charges
Requirements connected to commodity positions jumped 426% in the first quarter
Deutsche’s SVAR window update adds €2.2bn to RWAs
First-quarter surge comes after four consecutive reductions
Banks tout CCAR-style stress tests for emergent risks
Extreme-but-plausible scenario planning is being applied to geopolitical events such as Ukraine conflict
US unit of Barclays close to a VAR breach in Q4
Largest loss-to-VAR ratio at the firm was highest among 10 US intermediate holding companies
Banks balk at SEC backloading rule
Reporting requirements for expired security-based swaps “not justified”, dealers say
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
Quant funds tackle chronic overfitting in crypto strategies
Firms adapt backtests and tread lightly to address “huge” overfitting risk, magnified by scarce data
Citi leads US banks in shrinking market risk
First aggregate drop in capital charges stemming from market risk since mid-2020
BNY Mellon incurred a VAR breach in Q2
The highest losses-to-VAR ratio was 145.75%, in the first backtesting exception reported by the bank since 2018
Goldman’s market RWAs grew $14.9 billion in Q1
The increase was largely due to higher VAR and SVAR measures
Fake data can help backtesters, up to a point
Synthetic data made with machine learning will struggle to capture the caprice of financial markets
In fake data, quants see a fix for backtesting
Traditionally quants have learnt to pick data apart. Soon they might spend more time making it up
Model misfires raise questions over training data
Quants wrestle with how far into the past their machine learning models should peer
Factoring in Covid turmoil amped Bank of America's VAR in Q3
Value-at-risk averaged $109 million over three months to end-September
FRTB comes too late for Covid crisis
Expected shortfall would stop Basel 2.5 duplicate capital charges, but backtesting still a problem