Conference Day One

Main Conference Day 1: Thursday 1st October

08.00 – 09.00: Registration and Morning Welcome Coffee

All Streams

09.00 – 09.45: Legends in Quants Finance – Bruno Dupire introduced by Helyette Geman

Followed by Keynote address: “Imputing the Price of Options in the Absence of a Market”

Bruno Dupire:

Head of Quantitative Research, Bloomberg

Helyette Geman:

Ralph O’Connors Sustainable Energy Institute, Johns Hopkins University

All Streams

09.45 – 10.45: Panel: Topic to be confirmed

10.45 – 11.15: Morning Break and Networking Opportunities

Morning Stream Chair:

To be confirmed

AI / LLMs / ML Stream

11.15 – 12.00: “Beating the Memory Wall: Tile Computing Patterns for Quant Finance”

To be confirmed

Ioana Boier:

AI / LLMs / ML Stream

12.00 – 12.45: AI Model Risk: Measurement, Reporting and Mitigation

Alexander Sokol:

Head of Quant Research, CompatibL

12.45 – 14.00: Lunch

Afternoon Stream Chair:

To be confirmed

AI / LLMs / ML Stream

14.00 – 14.45: Practical Applications of Quantum Machine Learning in Quantitative Finance

Alexei Kondratyev:

Head of Risk at SW7 Group and Visiting Professor: Imperial College London

AI / LLMs / ML Stream

14.45 – 15.30: “Using GenAI to estimate Geographical Exposures and mitigate Geo-Biases”

Arun Verma:

Head of Quantitative Research Solutions, Bloomberg

15.30 – 16.00: Afternoon Break and Networking Opportunities

AI / LLMs / ML Stream

16.00 – 16.45: The 3 Steps to Optimal ML Function Approximation

Often, machine learning approaches struggle not due to lack of data or compute, but because they fail to address the fundamental mathematical challenges of high-dimensional approximation.

This talk outlines what is truly required—and what is not—to achieve robust ML approximation, focusing on key objectives: accuracy, fast evaluation, economically viable calibration, and full transparency.

We present a structured 3-step framework:

Managing the curse of dimensionality
Ensuring optimal convergence behaviour
Maintaining structural control of the approximation framework

Finally, we discuss the Model Risk Management implications, showing how a structured approach leads to more stable, explainable, and regulator-friendly models.

Ignacio Ruiz:

MoCaX Intelligence

AI / LLMs / ML Stream

16.45 – 17.30: ‘Meet Claire: Your AI Co-Trader’

Is an AI co-trader actually possible today (or just hype)?
What tasks it can reliably own vs what must stay human
Architecture: tools, data pipelines, execution layer, and infrastructure
Evals: measuring edge, robustness, and failure modes
Guardrails: risk limits, compliance constraints, monitoring, and kill switches

Valer Zetocha:

Senior Quantitative Analyst, ED, Julius Baer

Gala Dinner: Thursday 1st October, 20.00 til late.

Palazzo Preca Restaurant – The Gala Dinner is complimentary for all conference delegates.

At Palazzo Preca, we’re more than just a restaurant – we’re a celebration of the Preca family’s love of food and a tribute to their culinary legacy. Founded by sisters Ramona and Roberta Preca, our restaurant is the culmination of years of hard work, dedication, and a deep appreciation for the power of food to bring people together.

www.palazzoprecavalletta.com

Menu:

Starter

Braised Beef Ravioli
Homemade ravioli with braised beef served with sage & butter

Main Course

Sous Vide Supreme of Chicken
Served with Duxelle of Mushrooms of red wine jus

Dessert

Maltese Duo of Date Fritter & Rikotta Kannol

Beverages

Local wine
Local beer
Soft drinks
Water
Coffee

Information:

08.00 – 09.00: Registration and Morning Welcome Coffee

Volatility / Options / Monte Carlo Stream

09.00 – 09.45: Legends in Quants Finance – Bruno Dupire introduced by Helyette Geman

Followed by Keynote address: “Imputing the Price of Options in the Absence of a Market”

Bruno Dupire:

Head of Quantitative Research, Bloomberg

Helyette Geman:

Ralph O’Connors Sustainable Energy Institute, Johns Hopkins University

Volatility / Options / Monte Carlo Stream

09.45 – 10.45: Panel: Topic to be confirmed

10.45 – 11.15: Morning Break and Networking Opportunities

Morning Stream Chair:

To be confirmed

Volatility / Options / Monte Carlo Stream

11.15 – 12.00: Unsmooth: R-Functions in Option Pricing

We introduce an R-function–based framework for smoothing non-smooth option payoffs and stabilising Greek estimation. Standard numerical methods struggle with discontinuities arising in digital, barrier and path-dependent derivatives, leading to unstable sensitivities and degraded Quasi Monte Carlo (QMC) performance. Our approach reformulates payoff conditions as systems of inequalities and encodes them using R-functions, producing smooth, arbitrarily differentiable representations that preserve the original payoff logic and domain constraints. Numerical experiments show that the method significantly reduces variance and improves the robustness of Delta and Gamma estimates, particularly in QMC settings. Beyond option pricing, the framework naturally extends to portfolio risk aggregation, constraint modelling, XVA exposure profiles and optimisation problems involving complex logical conditions, offering a unified analytical tool for structured financial modelling.

Julien Hok:

Head of Quantitative Analysts, Investec Bank

Sergei Kucherenko

Senior Research Fellow, Imperial College

Volatility / Options / Monte Carlo Stream

12.00 – 12.45: Stochastic Implied Volatility, learned

We discuss learning the dynamics of option markets using of our smooth arbitrage-free non-parametric option surfaces (SANOS) under both the statistical and risk-neutral measure.

Hans Buehler:

Co-CEO XTX, Visiting Researcher, University of Oxford

12.45 – 14.00: Lunch

Afternoon Stream Chair:

Nikolai Nowaczyk:

Quantitative Analytics, Director, NatWest Group

Volatility / Options / Monte Carlo Stream

14.00 – 14.45: General Stochastic Local Volatility Models

New methologies for Monte Carlo calibration of local volatility overlay of general stochastic volatility models.
This includes multi-factor, path dependent, rough and tough variations.
Why risk reports in stochadtic local volatility models can be noisy and what to do about it.
Application to exotic option pricing: autocalls, barriers, cliquets, var/vol products.

Jesper Andreasen:

Head of Quantitative Analytics, Verition Fund Management LLC

Volatility / Options / Monte Carlo Stream

14.45 – 15.30: My Hot Shot Maverick Copula

Andrey Chirikhin:

Senior Credit Quant, Schonfeld

15.30 – 16.00: Afternoon Break and Networking Opportunities

Volatility / Options / Monte Carlo Stream

16.00 – 16.45: Autoencoder Manifolds and Mean Reversion Skew

Alexander Sokol:

Head of Quant Research, CompatibL

Volatility / Options / Monte Carlo Stream

16.45 – 17.30: Accurate Greeks for Non-smooth Payoffs through Smoothing Techniques Combined with AAD

Dmitri Goloubentsev:

CTO, Head of Automatic Adjoint Differentiation, Matlogica

Gala Dinner: Thursday 1st October, 20.00 til late.

Palazzo Preca Restaurant – The Gala Dinner is complimentary for all conference delegates.

www.palazzoprecavalletta.com

Menu:

Starter

Braised Beef Ravioli
Homemade ravioli with braised beef served with sage & butter

Main Course

Sous Vide Supreme of Chicken
Served with Duxelle of Mushrooms of red wine jus

Dessert

Maltese Duo of Date Fritter & Rikotta Kannol

Beverages

Local wine
Local beer
Soft drinks
Water
Coffee

Information:

08.00 – 09.00: Registration and Morning Welcome Coffee

All Streams

09.00 – 09.45: Legends in Quants Finance – Bruno Dupire introduced by Helyette Geman

Followed by Keynote address: “Imputing the Price of Options in the Absence of a Market”

Bruno Dupire:

Head of Quantitative Research, Bloomberg

Helyette Geman:

Ralph O’Connors Sustainable Energy Institute, Johns Hopkins University

All Streams

09.45 – 10.45: Panel: Topic to be confirmed

10.45 – 11.15: Morning Break and Networking Opportunities

Morning Stream Chair:

Saeed Amen

Turnleaf Analytics / Cuemacro / Visiting Lecturer at QMUL

Trading & Interest Rate Modelling Stream

11.15 – 12.00: ‘Betting Platforms and Arbitrage Trading ‘

Helyette Geman:

Ralph O’Connors Sustainable Energy Institute, Johns Hopkins University

Trading & Interest Rate Modelling Stream

12.00 – 12.45: Inflation, where will it be in 2027?

In this talk, we examine which CPI components are most important for driving headline inflation in the US. We discuss how we can approach forecasting inflation using machine learning models, and the types of data we can use for this. We also present some systematic trading strategies across macro markets using inflation forecasts as an input. We shall also be presenting some of forecasts for inflation going into 2027 for the major economies.

Saeed Amen

Turnleaf Analytics / Cuemacro / Visiting Lecturer at QMUL

12.45 – 14.00: Lunch

Afternoon Stream Chair:

To be confirmed

Marco Bianchetti:

Head of Market and Counterparty Risk IMA Methodologies, Intesa Sanpaolo

Trading & Interest Rate Modelling Stream

14.00 – 14.45: “Adding interest rate bounds without destroying analytical tractability”

Andrei Lyashenko:

Head of Market Risk and Pricing Models, Quantitative Risk Management (QRM), Inc.

Trading & Interest Rate Modelling Stream

14.45 – 15.30: Robust Lower Bound for a Bermudan Option

We derive a sharp model-independent lower bound for any twice-exercisable Bermudan
We characterise it as a dual to the optimal sub-hedge of a generalized spread type
We show that there exists a common model (measure) under which all Bermudans with the same exercise dates are priced at their individual lower bounds

Vladimir Piterbarg:

MD, Head of Quantitative Analytics and Quantitative Development, NatWest Markets

15.30 – 16.00: Afternoon Break and Networking Opportunities

Trading & Interest Rate Modelling Stream

16.00 – 16.45: Role of Central Banks: Implications for Rates Modelling and Pricing

Maria Makarova:

Vice President Quantitative Analyst, BNP Paribas

Vladimir Chorniy:

Managing Director, Head of Risk Model Fundamentals and Research Lab, Senior Technical Lead, BNP Paribas

Trading & Interest Rate Modelling Stream

16.45 – 17.30: Learning the Exact SABR Model

The pricing model calibration bottleneck
Theoretical framework: why SABR ?
Learning SABR with DNNs
Conclusions and perspectives

The SABR model is a cornerstone of interest rate volatility modeling, but its practical application relies heavily on the analytical approximation by Hagan et al., whose accuracy deteriorates for high volatility, long maturities, and out-of-the-money options, admitting arbitrage. While machine learning approaches have been proposed to overcome these limitations, they have often been limited by simplified SABR dynamics or a lack of systematic validation against the full spectrum of market conditions.
We develop a DNN SABR, a specialized Deep Neural Network (DNN) architecture that learns the true SABR stochastic dynamics using an very large training dataset (more than 200 million points) of interest rate Cap/Floor volatility surfaces, including very long maturities (30Y) and extreme strikes consistently with market quotations. Our dataset is obtained via high-precision unbiased Monte Carlo simulation of a special scaled shifted-SABR stochastic dynamics, which allows dimensional reduction without any loss of generality. Our SABR DNN provides arbitrage-free calibration of real market volatility surfaces and Cap/Floor prices for any maturity and strike with negligible computational effort and without retraining across business dates. Our results fully address the gaps in the previous machine learning SABR literature in a systematic and self-consistent way, and can be extended to cover any interest rate European options in different rate tenors and currencies, thus establishing a comprehensive functional SABR framework that can be adopted for daily trading and risk management activities.

Paper: arxiv.org/abs/2510.10343

Marco Bianchetti:

Head of Market and Counterparty Risk IMA Methodologies, Intesa Sanpaolo

Gala Dinner: Thursday 1st October, 20.00 til late.

Palazzo Preca Restaurant – The Gala Dinner is complimentary for all conference delegates.

www.palazzoprecavalletta.com

Menu:

Starter

Braised Beef Ravioli
Homemade ravioli with braised beef served with sage & butter

Main Course

Sous Vide Supreme of Chicken
Served with Duxelle of Mushrooms of red wine jus

Dessert

Maltese Duo of Date Fritter & Rikotta Kannol

Beverages

Local wine
Local beer
Soft drinks
Water
Coffee

Information: