Main Conference Day 2: Friday 2nd October
08.30 – 09.00: Morning Welcome Coffee
Morning Stream Chair:
To be confirmed
09.00 – 09.45: Pricing Derivatives with a Transformer-Based Approach
- Motivation: Deep Learning Approximations with Generative AI
- A Short History of Transformers
- An Introduction to the Attention Mechanism
- Transformers are Universal Approximators
- Regression Transformers
- Applications
Youssef Elouerkhaoui:
Managing Director, Global Head of Markets Quantitative Analysis, Citi
Youssef Elouerkhaoui:
Youssef Elouerkhaoui: Managing Director, Global Head of Markets Quantitative Analysis, Citi
Youssed Elouerkhaoui is the global Head of Credit Quantitive Analysis at Citi. His group supports all aspects of modelling and product development across desks, thais includes: Flow Credit Trading, Correlation Trading, CDOs, Exotics and Emering Markets.
He also supports CVA, Funding and Regulatory Capital for Credit Markets. Prior to this, he was a Director in the Fixed Income Derivatives Quantitative Research Group at UBS, where he was in charge of developing and implementing models for the Structured Credit Desk. Before joining UBS, Youssef was a Quantitative Research Analyst at Credit Lyonnais supporting the Interest Rates Exotics business. He has also worked as a Senior Consultant in the Risk Analytics and Research Group at Ernst & Young. He is a graduate of Ecole Centrale Paris and he holds a PhD in Mathematics from Paris-Dauphine University.
09.45 – 10.30: Multimodal models for asset price evolution
Blanka Horvath:
Associate Professor in Mathematical and Computational Finance, University of Oxford
Blanka Horvath:
Blanka Horvath: Associate Professor in Mathematical and Computational Finance, University of Oxford and Researcher, The Alan Turing Institute
Blanka research interests are in the area of Stochastic Analysis and Mathematical Finance.
Including asymptotic and numerical methods for option pricing, smile asymptotics for local- and stochastic volatility models (the SABR model and fractional volatility models in particular), Laplace methods on Wiener space and heat kernel expansions.
Blanka completed her PhD in Financial Mathematics at ETHZürich with Josef Teichmann and Johannes Muhle-Karbe. She holds a Diploma in Mathematics from the University of Bonn and an MSc in Economics from the University of Hong Kong.
10.30 – 11.00: Morning Break and Networking Opportunities
11.00 – 11.45: Breaking the Trend: How to Avoid Cherry-Picked Signals
Our empirical results show an impressive fit with the pretty complex theoretical Sharpe formula of a trend-following strategy depending on the parameter of the signal, which was derived by Grebenkov and Serror (2014). That empirical fit convinces us that a mean-Réversion process with only one time scale is enough to model, in a pret y precise way, the reality of the trend-following mechanism at the average scale of CTAs and as a consequence, using only one simple EMA, appears optimal to capture the trend. As a consequence, using a complex basket of different complex indicators as signal, do not seem to be so rational or optimal and exposes to the risk of cherry-picking.
Sébastien Valeyre:
Portfolio Manager, Machina Capital
Sébastien Valeyre:
Sébastien Valeyre: Portfolio Manager, Machina Capital
Sébastien Valeyre is the portfolio manager of Machina Capital’s systematic futures strategy, Machina Electron. Machina Capital is a Paris-based investment firm, founded by seasoned equity derivatives traders and quantitative researchers. The firm specializes in mid-frequency systematic strategies for equities and futures, aiming to generate absolute and uncorrelated returns.
Prior to joining Machina Capital, Sébastien was a partner at John Locke Investments, where he launched a statistical arbitrage fund, the John Locke Equity Market Neutral Fund. Sébastien successfully managed this equity strategy while also contributing research to the firm’s systematic CTA strategy. Before that, Sébastien was head of research at BPHI Capital, which employed a blended fundamental and quantitative approach. Sébastien began his career at France’s Authority of Nuclear Safety and Atomic Energy Commission.
Sébastien holds a PhD in Economics from Sorbonne Paris Cité University, a Master of Science from Imperial College, a Master of Science in Finance from Dauphine University, and a Master of Science in Physics from École Supérieure de Physique et Chimie Industrielles de Paris (ESPCI).
11.45 – 12.30: Self-Improving LLM-agents
Nicole Königstein:
Chief Data Scientist, Head of AI & Quant Research, Wyden Capital AG
Nicole Königstein:
Nicole Königstein: Chief Data Scientist, Head of AI & Quant Research, Wyden Capital AG
Nicole Königstein is a distinguished Data Scientist and Quantitative Researcher, currently working as Data Science and Technology Lead at impactvise, an ESG analytics company, and as Head of AI and Quantitative Research at Quantmate, an innovative FinTech startup focused on alternative data in predictive modeling. Alongside her roles in these organizations, she serves as an AI consultant across diverse industries, leading workshops and guiding companies from the conceptual stages of AI implementation through to final deployment.
As a guest lecturer, Nicole shares her expertise in Python, machine learning, and deep learning at various universities. She is a regular speaker at renowned AI and Data Science conferences, where she conducts workshops and educational sessions. In addition, she is an influential voice in the data science community, regularly reviewing books in her field and offering her insights and critiques. Nicole is also the author of the well-received online course, “Math for Machine Learning.
12.30 – 13.30: Lunch
Afternoon Stream Chair:
To be confirmed
13.30 – 14.15: Topic to be confirmed
Christopher Kantos:
Managing Director and Head of Quantitative Research, Alexandria Technology
Christopher Kantos:
Christopher Kantos: Managing Director and Head of Quantitative Research, Alexandria Technology
Mr. Christopher Kantos is a Managing Director and Head of Quantitative Research at Alexandria Technology. In this role, he focuses on maintaining and growing new business in EMEA, and exploring ways in which natural language processing and machine learning can be applied in the financial domain. Prior, he spent 15 years working in financial risk at Northfield Information Services as a Director and Senior Equity Risk Analyst. Mr. Kantos earned a BS in computer engineering from Tufts University.
14.15 – 15.00: Model Risk in the Age of Agentic AI
- From function validation to policy validation
- Fragility under perturbations and distribution shift
- Specification and objective misalignment
- Adversarial, generative validation frameworks
- Continuous assurance of non-stationary systems
Harsh Prasad:
Harsh Prasad:
Harsh Prasad: Principal & CEO, Qxplain
Harsh is the CEO of Qxplain, where he is working to help clients in the financial institutions develop and adopt more trustworthy AI models. He specializes in model risk management, AI/ML applications in finance, and GenAI product development. Prior to starting Qxplain, Harsh has over 20 years of experience in model development and validation where he led groundbreaking work in applying machine learning to the financial services industry. He has worked with Morgan Stanley, Nomura, EY and provided consultancy to GE Capital, Mubadala, Citi, BNP Paribas, London Stock Exchange Group and several other banks, funds, asset managers and family offices. He has taught at various universities, is the chair of CQF industry working group for data science and machine learning and conducts advanced trainings for machine learning in finance. He is an active researcher, thought leader and contributor in shaping the industry and regulatory best practice of model risk management for AI/ML models.
15.00 – 15.30: Afternoon Break and Networking Opportunities
15.30 – 16.15: Presenter & Topic to be confirmed
08.30 – 09.00: Morning Welcome Coffee
Morning Stream Chair:
To be confirmed
09.00 – 09.45: “Stretching Volatility Parametrizations with Random Coefficients”
- Implied volatility parametrizations are enhanced by randomizing the coefficients
- New parametrizations are semi-analytical and powerful enough to fit almost all market regimes
It is a market practice to express market-implied volatilities in some parametric form (SABR, SVI). These representations indirectly impose a model-specific volatility structure on observable market quotes. When the market’s volatility does not follow the parametric model regime, the calibration procedure will fail or lead to extreme parameters, indicating inconsistency. In this talk we propose an arbitrage-free framework for letting the parameters from the parametric implied volatility formula be random. The method enhances the existing parametrizations and enables a significant widening of the spectrum of permissible shapes of implied volatilities while preserving analyticity. We demonstrate the effectiveness of the novel method on real data from short-term index and equity options, where the standard parametrizations fail to capture market dynamics. Our results show that the proposed method is particularly powerful in modeling the implied volatility curves of short expiry options preceding an earnings announcement, when the risk-neutral probability density function exhibits a bimodal form.
Nicola Zaugg:
Quantitative Researcher, LGT Private Banking
Nicola Zaugg:
Nicola Zaugg: Quantitative Researcher, LGT Private Banking
Nicola Zaugg is a quantitative researcher in fixed income and derivatives at LGT Private Banking in Zurich. Alongside his industry role, he conducts academic research in financial mathematics in collaboration with Utrecht University in the Netherlands, contributing to research on derivatives pricing and volatility modeling. Prior to joining LGT, Nicola worked as a quantitative researcher at Rabobank in the Netherlands and at swissQuant in Zurich, Switzerland.
09.45 – 10.30: Convex Volatility Interpolation (CVI), an arbitrage-free volatility surface fitting methodology
- Arbitrage-free implied volatility surface fitting posed as a convex quadratic program in variance space
- Calendar spread no-arbitrage constraints are linear, butterfly no-arbitrage constraints are linearized
- Model-free, bid-ask-aware, no hyperparameter tuning (consistent across underlyings)
- Convexity guarantees a unique global optimum, eliminating the calibration fragility of traditional parametric models
- All expiries fitted jointly. Fit S&P 500 in a fraction of a second
Fabrice Deschâtres:
Founder and CEO, Volptima
Fabrice Deschâtres:
Fabrice Deschâtres: Founder and CEO, Volptima
Fabrice Deschâtres is the founder and CEO of Volptima, a Swiss fintech company commercialising Convex Volatility Interpolation (CVI), a high-performance, arbitrage-free volatility surface fitting methodology published in Risk.net’s Cutting Edge section in February 2026. Before founding Volptima, Fabrice held quantitative roles in derivatives pricing at Goldman Sachs, Millennium and Flow Traders. He is a graduate of the École Normale Supérieure (Ulm).
10.30 – 11.00: Morning Break and Networking Opportunities
11.00 – 11.45: Topic & Presenter to be confirmed
Julien Guyon:
Professor, ENPC, Institut Polytechnique de Paris & Visiting Associate Professor, NYU Tandon
Julien Guyon:
Julien Guyon: Professor, ENPC, Institut Polytechnique de Paris & Visiting Associate Professor, NYU Tandon
Julien is a former senior quantitative analyst in the Quantitative Research group at Bloomberg L.P., New York. He is also an adjunct professor in the Department of Mathematics at Columbia University and at the Courant Institute of Mathematical Sciences, NYU. Before joining Bloomberg, Julien worked in the Global Markets Quantitative Research team at Societe Generale in Paris for six years (2006-2012), and was an adjunct professor at Universite Paris 7 and Ecole des ponts. He co-authored the book Nonlinear Option Pricing (Chapman & Hall, CRC Financial Mathematics Series, 2014) with Pierre Henry-Labordere. His main research interests include nonlinear option pricing, volatility and correlation modeling, and numerical probabilistic methods. Julien holds a Ph.D. in Probability Theory and Statistics from Ecole des ponts. He graduated from Ecole Polytechnique (Paris), Universite Paris 6, and Ecole des ponts. A big football fan, Julien has also developed a strong interest in sports analytics, and has published several articles on the FIFA World Cup, the UEFA Champions League, and the UEFA Euro in top-tier newspapers such as The New York Times, Le Monde, and El Pais, including a new, fairer draw method for the FIFA World Cup.
11.45 – 12.30: Topic and Presenter to be confirmed
Vladimir Lucic
Head of Quants, Marex Solutions & Visiting Professor, Imperial College London
Vladimir Lucic
Vladimir Lucic: Head of Quants, Marex Solutions & Visiting Professor, Imperial College London
Over the years he occupied a number of quant roles in the industry, including the global head of Quantitative Analytics for Equity Derivatives and QIS (Barclays), Head of Volatility QIS (Macquarie Group) and others. He is also a non-exec director at RiskFuel. Vladimir has published in premier industry and theoretical journals.
12.30 – 13.30: Lunch
Afternoon Stream Chair:
To be confirmed
13.30 – 14.15: Decomposing Hedge Backtesting Results: Insights for Model Validation & Model Optimization
- Hedge backtesting is widely used in assessing models for pricing and hedging
- The combination of cloud computing and coding assistants can support more rapid iteration
- The literature on hedge backtesting as a formal tool for model validation is a little sparse
- Though the material there suggests a route to formalizing the analysis and bolstering heuristics
- We’ll pick up there and try to systematize things with the aid of some representative use cases
- We’ll also touch on tangential issues of model under-specification and historical calibration
Andrew McClelland:
Director, Quantitative Research, Numerix
Andrew McClelland:
Andrew McClelland: Director, Quantitative Research, Numerix
Andrew McClelland’s work at Numerix focuses on counterparty credit risk issues including valuation adjustments and counterparty exposure production for structured products. He also works on numerical methods for efficient production of risk profiles under real-world measures.
Andrew received his Ph.D. in finance at the Queensland University of Technology in financial econometrics. His research involved markets exhibiting crash feedback, option pricing, and parameter estimation using particle filtering methods. His work has been published in the Journal of Banking and Finance, the Journal of Econometrics, and the Journal of Business and Economic Statistics.
14.15 – 15.00: Topic and Presenter to be confirmed
15.00 – 15.30: Afternoon Break and Networking Opportunities
08.30 – 09.00: Morning Welcome Coffee
Morning Stream Chair: TBC
09.00 – 09.45: Extending VaR modelling capability to extreme scenario generation. EVT and copula implications
Vladimir Chorniy:
Managing Director, Head of Risk Model Fundamentals and Research Lab, Senior Technical Lead, BNP Paribas
Vladimir Chorniy:
Dorinel Bastide:
Senior Quantitative Analyst, BNP Paribas
Dorinel Bastide:
Dorinel Bastide: Senior Quantitative Analyst, BNP Paribas
Dorinel Bastide is a 20-year experienced senior quantitative researcher in risk management at BNP Paribas, covering clearing, systemic, operational, market, credit and climate modelling risks for XVAs, Reserves, Stress Test, ICAAP & IFRS9 metrics. He is a also member of BNP Paribas Risk Model Fundamentals and Research Lab. Dorinel is the coordinator for BNP Paribas of the research Chair Stress Test with Applied Mathematics Lab of French Ecole Polytechnique since 2018, responsible for organizing research events, designing and mentoring PhD projects in applied mathematics. He is a lecturer at French École Polytechnique within the MSc&T Data Science and AI for Business track. Dorinel holds a PhD in Applied Mathematics from University Paris-Saclay.
09.45 – 10.30: SPEC: A semi-parametric equity-credit model
Most counterparties do not have traded CDS instruments. This poses a challenge for calculating CVA which relies on risk-neutral default probabilities. Here we present a new model for the estimation of credit spreads using equity market data. In contrast to traditional equity-credit models, we take an empirical approach in order to determine a simple functional relationship that can be used in practice for CVA risk management. We find that our approach out-performs models that rely solely on credit data as well as alternative equity-credit models in the literature.
Matthias Arnsdorf:
Global head of Counterparty Credit Risk Quantitative Research, J.P. Morgan
Matthias Arnsdorf:
Matthias Arnsdorf: Global head of Counterparty Credit Risk Quantitative Research, J.P. Morgan
Since 2012 Matthias has been heading the counterparty credit risk quantitative research team globally.
His main responsibilities include the development & support of J.P. Morgan’s suite of credit exposure models which are used for valuation and risk management as well as credit capital.
Prior to his work in credit risk, Matthias headed the market risk capital modelling effort in EMEA for two years. Matthias started his career in finance in 2002 as a credit derivatives quantitative researcher at UBS and J.P.Morgan.
Matthias holds a PhD in Quantum Gravity from Imperial College London and has spent two years as a post-doctoral researcher at the Niels Bohr Institute in Copenhagen prior to his move to quantitative finance.
10.30 – 11.00: Morning Break and Networking Opportunities
11.00 – 11.45: Graphical Representation for Structured Finance and Payoffs
Jörg Kienitz:
Quant Finance and Machine Learning, Adjunct Prof (UCT), Assistant Prof (BUW), Naturfotograf
Jörg Kienitz:
Jörg Kienitz: Quant Finance and Machine Learning, Adjunct Prof (UCT), Assistant Prof (BUW), Naturfotograf
Jörg Kienitz is Director of Quantitative Methods, Olaf Dreyer and Ken Lichtner are Principle Consultants for Quantitative Methods at mrig – a Frankfurt based consultancy firm specialized on Quantitative Finance. Before joining mrig all three worked for different consultancy companies, banks or financial infrastructure providers. They cumulate decades of experience in the financial markets sector and are active in the academic research as well.
Ken Lichtner:
Principle Consultants for Quantitative Methods, m|rig GmbH
Ken Lichtner:
Ken Lichtner: Principle Consultants for Quantitative Methods, m|rig GmbH
Jörg Kienitz is Director of Quantitative Methods, Olaf Dreyer and Ken Lichtner are Principle Consultants for Quantitative Methods at mrig – a Frankfurt based consultancy firm specialized on Quantitative Finance. Before joining mrig all three worked for different consultancy companies, banks or financial infrastructure providers. They cumulate decades of experience in the financial markets sector and are active in the academic research as well.
Olaf Dreyer:
Principle Consultants for Quantitative Methods, m|rig GmbH
Olaf Dreyer:
Olaf Dreyer: Principle Consultants for Quantitative Methods, m|rig GmbH
Jörg Kienitz is Director of Quantitative Methods, Olaf Dreyer and Ken Lichtner are Principle Consultants for Quantitative Methods at mrig – a Frankfurt based consultancy firm specialized on Quantitative Finance. Before joining mrig all three worked for different consultancy companies, banks or financial infrastructure providers. They cumulate decades of experience in the financial markets sector and are active in the academic research as well.
11.45 – 12.30: Rethinking Factor Models: Consistent Risk-Return Architecture via Hierarchical Group LASSO
- Industry-standard factor models (Barra, Bloomberg) are risk-only by design — they provide covariance but not expected returns, forcing a structural disconnect between risk and return inputs to the optimizer
- When expected returns are not spanned by the risk model’s factor structure, the optimizer treats the unpriced component as free alpha, systematically underestimating portfolio risk
- The MATF framework resolves this by deriving both expected returns and covariance from a single sparse factor loading matrix estimated across eight tradable risk premia
- The underlying HCGL estimator — with sign constraints, prior-centered regularisation, and integrated covariance assembly — is released as the open-source Python package factorlasso
- Factor-structured assumptions reduce frontier estimation uncertainty and propagate scenario stress coherently across all assets through a single factor-level shift
- This presentation is based on:
- Sepp, A., I. Ossa, and M.A. Kastenholz (2026), “Robust Optimization of Strategic and Tactical Asset Allocation for Multi-Asset Portfolios,” The Journal of Portfolio Management, 52(4), 86–120
- Sepp, A., E. Hansen, and M.A. Kastenholz (2026), “Capital Market Assumptions and Strategic Asset Allocation Using Multi-Asset Tradable Factors,” under revision at The Journal of Portfolio Management
Artur Sepp:
Head Quant, LGT Bank
Artur Sepp:
Artur Sepp: Head Quant, LGT Bank
Artur Sepp is the Global Head of Quantitative Analytics at LGT Bank in Zurich, where he leads a global quant team and architects the systematic investment platform for portfolio construction. He advances quantitative portfolio management through research, technology, and team development to deliver investment solutions aligned with LGT’s long-term perspective and pursuit of excellence. Named Risk Magazine’s Quant of the Year 2024, he brings over 20 years of experience spanning both the buy-side and sell-side. This cross-domain career has defined his research signature: solving applied problems by connecting ideas across asset classes and disciplines. He holds a PhD in Mathematical Statistics from the University of Tartu, with over 1,200 citations and an H-index of 18, with research spanning portfolio optimization, stochastic volatility, systematic strategies, machine learning, and blockchain/DeFi. His contributions include the ROSAA (Robust Optimization of Strategic and Active Asset Allocation) framework and the log-normal beta stochastic volatility model. He serves on the editorial board of The Journal of Computational Finance and co-develops open-source Python libraries for quantitative finance. Outside of finance, Artur is a dedicated Brazilian Jiu-Jitsu practitioner and purple belt holder, where the lessons from the mat – patience, adaptability, and problem-solving under pressure – carry over to his life.
12.30 – 13.30: Lunch
Afternoon Stream Chair:
To be confirmed
13.30 – 14.15: FRTB IMA: Quo Vadis? Internal Models at Crossroads: Proposing simple solutions to revive IMA adoption
Eduardo Epperlein:
Eduardo Epperlein:
Eduardo Epperlein has 30 years’ experience in the financial industry. Prior to joining Nomura, Eduardo held various roles in risk methodology at Citigroup, including model validation. Eduardo holds a PhD in Plasma Physics from Imperial College, London, and spent 10 years as a research scientist prior to joining the financial industry.
14.15 – 15.00: Topic to be confirmed
Maurizio Garro:
CFO and Head of Business Development, My Alpha investment FZCO
Maurizio Garro:
Maurizio Garro: CFO and Head of Business Development, My Alpha investment FZCO
Maurizio Garro works as a CFO and Head of Business Development at My Alpha investment FZCO. Previusly he was the senior Lead BA for the IBOR Transition programme at Lloyds Banking Group, where he lead the delivery of the changes required for models, curves and products for the transition to the alternative risk-free rates for the Front and Back book. His background is in quantitative risk management, Model Risk, Market Risk, Counterparty Credit Risk, Pricing, Liquidity and Stress Testing.
He has a long-standing experience as an internal auditor, consultant and banker in model risk management and previously worked in the Development and Validation teams of top-tier financial institutions in Europe, U.S., and the U.K. for over 15 years.
Maurizio is a frequent speaker on various topics in risk management, a member of the Institute of Internal Auditor and the Director of the Global Association of Risk Professional (GARP) London Chapter.
Maurizio Garro received his Master Degree in Economics from the Bocconi University of Milano and a certificate in Financial Risk Management (FRM) from GARP.
