Main Conference Day Two - GMT (Greenwich Mean Time, GMTZ)
Alternative data is no longer an edge – it’s an expectation. From satellite imagery to payment flows and ESG sentiment, the challenge has sifted from sourcing to signal extraction, integration, and regulatory defensibility. How are quant teams turning noise into scalable alpha across asset classes?
Exclusive guest speaker address
- Mahdi Anvari - Head of Equity Derivatives Quantitative Analysis, Millennium
- Stability and accuracy of fd solution: myths, facts and orthodoxy
- Discrete consistency: backwards, forwards, dupire and monte carlo
- Dividends, stochastic volatility, jumps
- Monte-carlo simulation, likelihood ratio tricks and adjoint differentiation
- Jesper Andreasen - Head of Quantitative Analytics, Verition Fund Management
How containers enable real-time speed
Breaking latency with modular design
From edge computing to execution
Speed, interpretability, and overfitting risk
Convexity in cross-asset stress
Volatility clustering meets capital thresholds
How can big data be harnessed for volatility and trading? What is the role of ML?
Black Scholes, local volatility, and stochastic models
From prototype to production safely
Stochastic modelling meets deep learning
Interpreting models under Basel III
Applying annealing in non-convex spaces
Exploiting slippage in factor drift
Extracting alpha from analyst tone
When bid offer becomes portfolio drag
From copulas to contagion simulation
How synchrony breaks diversification logic
Developments and innovation
Combining the best aspects of entropy and volatility with respect to option pricing
- Mahdi Anvari - Head of Equity Derivatives Quantitative Analysis, Millennium
Latency, memory, and compilation trade-offs
Hardware choices for model acceleration
From notebook to deployment fast
From priors to robust allocation
Adjusting exposure to volatility shocks
Scaling allocation across correlated trees
Exposure rises with credit deterioration
Interbank dependencies under fragility stress
Extracting forward credit risk signals
From structured notes to volatility-linked products, what's driving client demand and innovation?
How are teams evolving infrastructure to handle large-scale data, model governance, and MLOps?
What models, signals, or frameworks are helping navigate macro uncertainty and asset correlation shifts?
Where are the blind spots when models break under stress, and how can risk teams prepare?