World Business StrategiesServing the Global Financial Community since 2000

Main Conference Day 1:

Thursday 18th May

08.00 – 09.00: Registration and Morning Welcome Coffee

AI & Machine Learning Stream

09.00 – 09.45: Generative Deep Learning in Quant Finance

Andrew Green: 

Managing Director and Lead GFI Quant, Scotiabank
AI & Machine Learning Stream

09.45 – 10.30: Autoencoder Market Models for Interest Rates

Alexander Sokol:

Executive Chairman and Head of Quant Research, CompatibL

10.30 – 11.00: Morning Break and Networking Opportunities

AI & Machine Learning Stream

11.00 – 11.45: Derivatives Pricing with Sobolev Deep Learning

  • Motivation: Fast and Stable Deep Learning
  • An Introduction to Sobolev Deep Learning Universal Representation
  • Theorem on Sobolev Spaces
  • Practical Numerical Implementation Applications

Youssef Elouerkhaoui:

Managing Director, Global Head of Markets Quantitative Analysis, Citi

AI & Machine Learning Stream

11.45 – 12.30: Model-Agnostic Pricing of Exotic Derivatives Using Signatures

Andrew Alden

PhD student, Mathematical and Computational Finance, King’s College London

Blanka Horvath:

Associate Professor in Mathematical and Computational Finance, University of Oxford

Gordon Lee:

Head of XVA and Derivatives Quantitative Analytics, BNY Mellon

12.30 – 13.30: Lunch

AI & Machine Learning Stream

13.30 – 14.15: The Future of Asset Allocation: Exploring the Potential of Language AI

Abstract:  In this presentation, we’ll explore the potential of language AI in asset allocation. We’ll discuss how real-time news analytics can navigate the business cycles and aid in asset-class rotation, and how sentiment analysis can inform sector selection strategies, with the added layer of corporate controversy filters. Understanding the capabilities of language AI in asset allocation can equip us to make better-informed investment decisions and augment market timing abilities.

Peter Hafez:

Chief Data Scientist, RavenPack

AI & Machine Learning Stream

14.15 – 15.00: Distributional Imputation for Volatility Surfaces using Variational Autoencoders

Abstract: We review the usage of variational autoencoders (VAEs) for imputing FX volatility surfaces, discuss common misconceptions and misuses of VAEs, the importance of architecture, and finally how to use VAEs for imputing with uncertainties.

Achintya Gopal:

Machine Learning Quant Researcher, Bloomberg

15.00 – 15.30: Afternoon Break and Networking Opportunities

AI & Machine Learning Stream

15.30 – 16.15: Semi-Analytic Conditional Expectations and Applications

We introduce a data driven and model free approach for computing conditional expectations. The new method combines Gaussian Mean Mixture models with classic analytic techniques based on the properties of the Gaussian distribution. As applications we consider

  • Proxy hedges
  • Bermudan options
  • Stochastic Local Volatility
  • Forward Backward Stochastic Differential Equations

Jörg Kienitz:

Independent Consultant, Adjunct Prof (UCT), Assistant Prof (BUW)

AI & Machine Learning Stream

16.15 – 17.00: Risk Analytics in the Age of AI, with a case study on wrong way risk

Abstract: The field of Risk Analytics is long overdue for deep renewal, and the introduction of AGI platforms is poised to act as a catalyst for this change. We will explore a case-study on Clearing Analytics, including a discussion of margin models, wrong-way-risk add-ons, hypothetical scenarios, default fund contributions, reverse stress testing, market data analytics, and firm valuation. Additionally, we will delve into how LLMs and new mathematical and software engineering technologies are expected to revolutionize the risk-analytics domain. We will focus primarily on Clearing House analytics, but similar considerations extend to banking, insurance, and buy-side investment houses alike.

Claudio Albanese:

Founder, Global Valuation

AI & Machine Learning Stream

17.00 – 18.00: AI and ML in Quant Finance Panel

Large Language Models (LLM) in quant finance – a gimmick or a game changer?

  • Will LLMs revolutionize fundamental analysis?
  • Will LLMs revolutionize sentiment analysis?
  • Will LLMs enable the use of alternative data in new ways?
  • Does LLMs have a role in integrating ESG in the investment process?

ML models for valuation, XVA, and risk

  • How to build trustworthy ML quant models that auditors and regulators will approve
  • Due to the lack of sufficient training data, is ML in quant models truly learning or only providing a better way to interpolate

Moderator:

Alexander Sokol:

Executive Chairman and Head of Quant Research, CompatibL

Blanka Horvath:

Associate Professor in Mathematical and Computational Finance, University of Oxford

Gordon Lee:

Head of XVA and Derivatives Quantitative Analytics, BNY Mellon

Jörg Kienitz:

Independent Consultant, Adjunct Prof (UCT), Assistant Prof (BUW)

Peter Hafez:

Chief Data Scientist, RavenPack

18.00 – 19.30: Drinks Reception

08.00 – 09.00: Registration and Morning Welcome Coffee

Latest Quantitative Modelling & Regulations Stream

09.00 – 09.45: Latest FRTB Update

Adolfo Montoro:

Director, Global Market Risk Analytics, Bank of America

Latest Quantitative Modelling & Regulations Stream

09.45 – 10.30: Counting jumps: an analysis of different waiting time distributions. Applications in Finance.

Co-authored with Gianluca Fusai and Daniele Marazzina.

Laura Ballotta:

Prof. of Mathematical Finance, Bayes Business School (formerly Cass)

10.30 – 11.00: Morning Break and Networking Opportunities

Latest Quantitative Modelling & Regulations Stream

11.00 – 11.45: Leveraged Wrong-Way Risk

We introduce a simple model for the credit exposure to leveraged and collateralized counter-parties. Wrong-way risk is captured by linking the counter-party default probability directly to changes in the portfolio value. This applies e.g. to leveraged firms such as hedge funds where large collateral calls can be the driver of default. We show that our model is able to reproduce the large losses observed in recent events. These losses were unexpected based on typical exposure models which neglect the relatedness of large market moves and the viability of the counter-party. Our model is intuitive to parameterize and straightforward to implement and thus provides a useful tool for assessing the credit risk inherent in leveraged portfolios.

Matthias Arnsdorf:

Global head of Counterparty Credit Risk Quantitative Research, J.P. Morgan

Latest Quantitative Modelling & Regulations Stream

11.45 – 12.30: Modeling Yield Curves with Factor HJM

We present a new interest rate modeling framework based on the factor modeling approach widely used to model yield curves in real-world applications. The new modeling framework is very attractive as it combines the simplicity, intuitiveness, and computational efficiency of the factor modeling approach with the rigor of no-arbitrage term structure pricing models.

Andrei Lyashenko:

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

12.30 – 13.30: Lunch

Latest Quantitative Modelling & Regulations Stream

13.30 – 14.15: Joint Modelling of CMS rates in a Risk-Free Rate framework

Elias Daboussi:

Quantitative Analyst, Bank of America Merrill Lynch

Latest Quantitative Modelling & Regulations Stream

14.15 – 15.00: Efficient Valuation of Mid-curve Swaptions

Abstract: We consider a model for midcurves that that respects relevant swaption skews, allows a flexible correlation structure and accounts for the stochasticity of annuities. Furthermore, we present a method to evaluate the model efficiently.

Wen Jiang

Executive Director, Head of Structured Rates Quantitative Research, Nomura

15.00 – 15.30: Afternoon Break and Networking Opportunities

Latest Quantitative Modelling & Regulations Stream

15.30 – 16.15: Analytic RFR Option Pricing with Smile and Skew

Colin Turfus:

Quantitative Analyst, Deutsche Bank

Latest Quantitative Modelling & Regulations Stream

16.15 – 17.00: Collateralised Exposure Modelling: Bridging the Gap Risk

Fabrizio Anfuso:

Traded Risk Measurement, PRA, Bank of England

Both Streams

17.00 – 18.00: AI and ML in Quant Finance Panel

Large Language Models (LLM) in quant finance – a gimmick or a game changer?

  • Will LLMs revolutionize fundamental analysis?
  • Will LLMs revolutionize sentiment analysis?
  • Will LLMs enable the use of alternative data in new ways?
  • Does LLMs have a role in integrating ESG in the investment process?

ML models for valuation, XVA, and risk

  • How to build trustworthy ML quant models that auditors and regulators will approve
  • Due to the lack of sufficient training data, is ML in quant models truly learning or only providing a better way to interpolate

Moderator:

Alexander Sokol:

Executive Chairman and Head of Quant Research, CompatibL

Blanka Horvath:

Associate Professor in Mathematical and Computational Finance, University of Oxford

Gordon Lee:

Head of XVA and Derivatives Quantitative Analytics, BNY Mellon

Jörg Kienitz:

Independent Consultant, Adjunct Prof (UCT), Assistant Prof (BUW)

Peter Hafez:

Chief Data Scientist, RavenPack

18.00 – 19.30: Drinks Reception

  • Discount Structure
  • Special Offer
    When two colleagues attend the 3rd goes free!

  • 70% Academic Discount
    (FULL-TIME Students Only)

Event Email Reminder

Error

Also attend