Main Conference Day Three - GMT (Greenwich Mean Time, GMTZ)
From realised volatility to gamma
Joint dynamics for multi risk pricing
From baskets to dispersion trades
- Davide Venturelli - Associate Director - Quantum Computing & Research Scientist, USRA
Where are we now? Where are we headed? What are the current practical applications?
How do we expect quantum ML to play a sharper role in finance that modern ML?
Although recent advances have made it feasible to estimate dynamic covariance matrices in high dimensions, portfolio managers face significant model risk when selecting a single forecast approach. We propose several forecast combination methods to mitigate model uncertainty and the risk of relative underperformance. These include distance-based approaches that penalize models producing forecasts that diverge excessively from others, as well as two optimization-based methods, which balance variance reduction with portfolio stability relative to individual models. Using daily U.S. stock data from 1980 to 2022, we evaluate ten individual covariance forecasting models and several combination strategies, constructing long-only minimum variance portfolios for universes of up to 1000 stocks. Forecast combinations--particularly simple ones--reduce model risk and deliver realized volatility close to the best individual models. However, optimization-based combinations often introduce additional turnover, potentially offsetting their benefits after transaction costs. Our results highlight the trade-off between improved risk forecasts and higher turnover, suggesting turnover-aware forecast combination as a direction for future research.
- Alexandre Rubesam - Associate Professor of Finance, IÉSEG School of Management
From credit spreads to FX
Unifying yield curves with momentum
When CDS markets aren’t liquid
From clearinghouse links to capital flows
Stress scenarios meet non-modellability
Capturing risk in volatile bursts
Separating shape from market beliefs
From theoretical alpha to P&L
Bridging signals with real fills
VAR vs ES with flawed inputs
Worst-case loss as hedge driver
From utility to payout calibration
From inventory to market impact
Encoding sequences for financial prediction
Failover, scaling, and cost routing
Privacy-preserving validation at scale
Balancing beta drift and exposure
From tight spreads to tail risk
Global regulatory factors and considerations for credit risk modelling
When models learn hedge slippage
Replicating beta using swaps
Structured payoffs with dynamic risk
From action-value to optimal spread
Index alpha with similarity search
State transitions inform allocation shifts
Creating edge from latent space
Crisis alpha from convex payoffs
From live ticks to red flags