Beyond VaR: A New Approach to Banking Risk

The analysis exposes the extreme tail risk within the banking sector, quantifying potential losses at the $99.9\%$ confidence level using both Value at Risk (VaR) and Expected Shortfall (ES) metrics, thereby illuminating the magnitude of credit risk exposure.

Traditional risk measures often fall short in capturing the full spectrum of potential losses, and this research proposes a refined framework based on magnitude and propensity to provide a more nuanced assessment.

Can AI Spot Trouble on the Grid?

New research shows that artificial intelligence models can effectively identify anomalies in power system data, offering a promising path toward more reliable and resilient energy infrastructure.