• Understand the impact of machine learning on empirical finance
• Evaluate where traditional econometrics and AI converge and diverge
• Explore practical implications for systematic investing
Discussion Points:
Discussion Points:
• Share practical examples of multi-asset signal construction and validation
• Discuss infrastructure needed for cross-asset strategy integration
• Explore alpha decay and diversification techniques
Discussion Points:
In this keynote, Sébastien Laurent draws on his deep expertise in econometrics to challenge the current state of volatility modelling and explore cutting-edge methodologies for assessing and forecasting conditional risk in complex portfolios.
Key Topics Covered:
• Volatility of market risk: structural shifts, clustering, and asymmetric responses
• Understanding the link between model precision and portfolio robustness
• The trade-off between complexity and interpretability in high-stakes risk modelling
• Practical implications of risk misestimation on capital allocation and stress testing
Discussion Points:
• The role of macroeconomic modelling in stress testing and capital planning and assessing GDP sensitivity and scenario planning under market shocks
• Challenges in validating econometric models for dynamic policy environments
• Quantamental Approaches in Model Development
• Linking model outputs to P&L and strategic asset allocation decisions
Key Topics Covered:
• How advanced machine learning is improving short- and medium-term return forecasts, volatility modelling, and regime detection
• Incorporating predictive models into asset allocation while managing slippage, liquidity, and real-world frictions
• Extracting structured signals from unstructured data, news, earnings calls, filings, and social media, to enhance portfolio insights
• Frameworks for deciding when and how to deploy ML, LLMs, or agentic AI—balancing interpretability, speed, complexity, and impact
• Organizational readiness -considerations in deploying next-gen AI in investment workflows
This Session Is for You If:
• You know nothing about AI and want a clear, jargon-free introduction—grounded in market reality, not tech utopia.
• You know everything about AI but are tired of hype, academic detachment, and ineffective implementations.
Masterclass Objectives:
1. Cut through the noise: Understand what AI/ML can do in trading, and where it's often misunderstood.
2. Explore real-world AI/ML models that work—and why most don’t.
3. Learn how to validate whether your AI investment is delivering financial impact.
4. Build a functional bridge between finance, modeling, and machine learning.
5. Apply critical thinking to AI adoption in financial markets.
Discussion Points:
Discussion Points:
• Navigating the trade-off between flexibility and maintainability
• Building elastic systems that respond to shifts in flow, volatility, and client behaviour
• How firms are balancing infrastructure optimization with bespoke analytics and tooling
• API-first, interoperable components for OMS/EMS, analytics, risk, and trade lifecycle
• Using ML agents, LLMs, and automation to deliver custom reporting, real-time recommendations, and adaptive trading strategies
• How infrastructure modernization directly enables new revenue streams, faster product rollout, and differentiated client experience
Discussion Points:
This in-depth technical masterclass is designed for quants, risk analysts, and portfolio managers looking to elevate their modeling skills for market risk management. Sébastien Laurent leads a hands-on session focused on the practical implementation of advanced techniques in volatility modeling, dimensionality reduction, and time-varying systems.
Key Concepts Discussed:
Estimating and evaluating conditional variance dynamics using modern econometric tools
Addressing dimensionality in risk models: factor selection, shrinkage, and feature extraction
Implementing regularisation techniques for robust portfolio and factor modeling
Working with time-varying parameter models: stability, responsiveness, and predictive power
Developing precision metrics for model validation and out-of-sample performance
Format & Structure:
Interactive lecture format
Use of case studies and real-world datasets (financial time series)
Live Q&A and peer discussion of implementation challenges
Target Audience:
Quantitative analysts, risk managers, academic researchers, portfolio quants, and model validation teams
Discussion Points:
Designed for Quants and voted for by Quantitative Strategists - Join us for a few drinks as we reveal who the Top 10 innovators, globally