World Business StrategiesServing the Global Financial Community since 2000

Wednesday 16th October

The Future of LIBOR: Quantitative Perspective on Benchmarks, Overnight, Fallback and Regulation.

With the increased expectation of some IBORs discontinuation and the increasing regulatory
requirements related to benchmarks, a more robust fallback provision and a clear transition plan for benchmark-linked derivatives is becoming paramount for the interest rate market.

The recent regulations include the EU Benchmark Regulation (BMR) which may have a severe impact on the EUR market as early as January 2020. For all major currencies, new benchmarks have been proposed and the market are in a transition phase. Each transition has his idiosyn- crasies and a commun transition approach cannot be expected. We also describe the new products associated to the new benchmarks and the status in term of liquidity for each market.

On the fallback side, several options have been proposed and ISDA held a consultation on
some of them. The results of the ISDA consultation has been to select the\compounding setting in arrears” adjusted rate and the “historical mean/median” spread approach. We analyse the proposed options in details and present an alternative option supported by different working groups. The presentation focuses is on the quantitative nance impacts for derivatives.

Agenda:

Cash-collateral discounting.

  • The standard collateral results and their exact application.
  • What is hidden behind OIS discounting (and when it cannot be used)?
  • Impact of new benchmarks on valuation

EU Benchmark regulation
The\alternative” benchmarks:

  • SOFR, reformed SONIA, ESTER, SARON, TONAR.
  • Secured v unsecured choice.
  • What about term rates?
  • Curve calibration
  • SOFR and EFFR: two overnight rates in one currency!

Status in different currencies. Cleared OTC products, liquidity. The di erent consultations
in progress and what to expect from them.
Fallback procedure

  • ISDA consultation results
  • The adjusted rate: compounding setting in arrears
  • The adjustment spread: historical mean/median approach
  • Quantitative issues with compounding setting in arrears
  • Term rates: a credible alternative?
  • Value transfer: transfers already incorporated and transfers to come

Clearing House doption

  • Differences between bilateral and CCP rules
  • EFFR to SOFR transition in USD

Risk management of the fallback

  • Delta risk through the transition
  • Potential impacts on systems
  • What a risk solution would look like
  • Multi-curve: double or quit?
  • Vanilla becoming exotics: cap/ oor and swaptions

New products associated to new benchmarks

  • Volume and liquidity in the new benchmarks
  • Futures on overnight benchmarks
  • Deliverable swap futures

Detailed lecture notes for participants.
Some details will be adapted to the evolution of the market.

Speaker

Marc Henrard:

Managing Partner muRisQ Advisory and Visiting Professor, University College London

Marc Henrard: Managing Partner muRisQ Advisory and Visiting Professor, University College London

Over the last 20 years, Marc has worked in various areas of quantitative finance. Marc’s career includes Head of Quantitative Research at OpenGamma, Global Head of Interest Rate Modeling for Dexia Group, Head of Quantitative Research and Deputy Head of Interest Rate Trading at the Bank for International Settlements (BIS) and Deputy Head of Treasury Risk also at BIS.

Marc’s research focuses on interest rate modeling and risk management. More recently he focused his attention to market infrastructure (CCP and bilateral margin, exchange traded product design, regulatory costs). He publishes on a regular basis in international finance journals, and is a frequent speaker at academic and practitioner conferences. He recently authored two books: The multi-curve framework: foundation, evolution, implementation and Algorithmic Differentiation in Finance Explained.

Marc holds a PhD in Mathematics from the University of Louvain, Belgium. He has been research scientist and university lecturer in Belgium, Italy, Chile and the United Kingdom.

Workshop Schedule: 09:00 – 17:30

Break: 10:30 – 11:00
Lunch: 12:30 – 13:30
Break: 15:15 – 15:30

Wednesday 16th October

Back-propagation and Automatic Adjoint Differentiation (AAD) in Machine Learning and Finance

  • Introduction to Artificial Neural Networks and Deep Learning
  • Back-propagation through ANNs
  • Applications of ANNs and back-prop in finance
  • Hands-on examples with Python and Tensor Flow
  • How to extract computation graphs to differentiate arbitrary calculations
  • Fast (reverse mode) AAD with operator overloading in C++
  • Application to financial risk management
  • Hands-on examples in (basic) C++ with Dupire’s model and Monte-Carlo simulations

This workshop includes a complimentary copy of Modern Computational Finance: AAD and Parallel Simulations by Antoine Savine

Speaker

Antoine Savine:

Quantitative Research, Danske Bank

Antoine Savine: Quantitative Research, Danske Bank

Antoine Savine has worked for various Investment Banks since 1995, along Bruno Dupire, Leif Andersen and Marek Musiela. He was Global Head of Quantitative Research for Fixed Income, Currency and Credit Derivatives for BNP-Paribas 1999-2009, and currently works in Copenhagen for Danske Bank, where his work with Jesper Andreasen earned the In-House System of the Year 2015 Risk Award. His upcoming publications in Wiley’s Computational Finance series are dedicated to teaching the technologies implemented in those award-winning systems.

Antoine also teaches Volatility Modeling and Numerical Finance in the University of Copenhagen’s Masters of Science in Mathematics-Economics. The curriculum for his Numerical Finance lectures is being published by Wiley under the name “AAD and Parallel Simulations”.

Antoine holds a Masters from the University of Paris (Jussieu) and a PhD from the University of Copenhagen, both in Mathematics.

Workshop Schedule: 09:00 – 17:30

Break: 10:30 – 11:00
Lunch: 12:30 – 13:30
Break: 15:15 – 15:30

Wednesday 16th October

Machine Learning for Option Pricing

The goal of this workshop is to provide a detailed overview of machine learning techniques applied for finance. We offer insights into the latest techniques of using such techniques for modelling financial markets where we focus on pricing and calibration.

We not only tackle the theory but give practical guidance and live demonstrations of the computational methods involved. After introducing the subject we cover Gaussian Process Regression and Artifical Neural Networks and show how such methods can be applied to solve option pricing problems, speed up the calculation of xVAs or apply them for hedging.

We further show how to use existing pricing libraries to interact with machine learning environments often set up in Python. To this end we consider the interaction with Excel, C++ (QuantLib/ORE) and Matlab.

We explain how to set up the methods in Matlab and Python using Keras, Tensorflow, SciKit and PyTorch by explaining the implementation on Matlab source code as well as Jupyther notebooks.

This workshop covers the fundamentals and illustrates the application of state-of-the-art machine learning applications in the financial markets. The examples used for illustration are given to the delegates after the course.

Course Highlights

This workshop covers the latest techniques for mastering the application of Gaussian Process Regression methods and Artificial Neural Networks techniques. We consider the theoretical underpinnings and give finance related examples in Matlab and/or Python.

Especially we cover

  • Overview of some Machine Learning techniques
  • Implementation and Examples
  • Gaussian Process Regression for option pricing
  • The maths of Neural Networks (with examples)
  • Deep learning for pricing using the Heston and other SV models
  • Deep learning for calibrating Stochastic Volatility Models

Course Methodology

  • Presentation
  • Examples (Matlab/Jupyter Notebooks)

Contents of Workshop

Machine Learning and Finance Overview

  • Machine Learning
    • Supervised Learning for Classification, Regression
    • Unsupervised Learning
    • Selfsupervised Learning
    • Reinforcement Learning
  • Finance
    • Pricing and hedging
    • Calibration
    • Simulation and exposure
    • Fraud detection

Machine Learning and Finance – Programming Overview

  • ML and Financial Applications – an overview
    • Python, Tensorflow, Keras
    • C++, Java, Matlab, QuantLib/ORE
  • Interfacing
    • Python – Excel
    • Python – QuantLib/ORE
    • Python – Matlab
  • Some illustrations
    • Exposure for Bermudan Swaptions in Tensorflow
    • Hull-White with PDE in Python using QL
    • Monte Carlo Simulation in Tensorflow

Gaussian Process Regression (GPR)

  • Intro to GPR and Regression
    • How does it work?
    • Train, Validate, Test
    • Covariance Functions
  • Pricing Models and Methods
  • GPR and Option Pricing (Heston, American Options,…)

Artificial Neural Networks in Finance – introduction and examples I

  • Intro to Artificial Neural Networks
    • Construction
    • ANN at work
  • ANN math recap (with examples)
    • on Linear Algebra: Points, Vectors, Matrices, Tensors,…
    • on Optimization: Gradient Descent, …
    • on Autodifferentiation
  • Illustration: Learning a function
  • It’s only an approximation!
  • Illustration:
    • Black-Scholes Merton Model
    • Heston Model
    • SABR Model
  • Observations
  • Preprocessing/Feature engineering
  • Overfitting / Underfitting
  • Train, Validate, Test
  • Hyperparameters
  • Different Types of Networks
    • FFNN – Feed Forward
    • CNN – Convolutional
    • RNN – Recursive
    • LSTM – Long Short Term Memory
    • GAN – General Adversial
    • Autoencoders

Artificial Neural Networks in Finance – introduction and examples II

  • Calibration Basics
  • Illustration: Deep Calibration
    • Heston Model
    • SABR Model
  • Hedging Basics
  • LSTM revisited
  • Illustration: Deep Hedging
  • (Time Series Analysis and Forecasting

Matlab Code / Jupyter Notebooks are provided for this workshop 

Jörg Kienitz:

Partner, Quaternion Risk Management

Jörg Kienitz: Partner, Quaternion Risk Management

Previously: Director FSI Assurance Deloitte GmbH and Co-Head of Quant Unit, Head of Quantitative Analytics, Dt. Postbank AG, Senior System Architect, Postbank Systems AG Financial Consultant, Reuters; Academic: Adj. Assoc. Prof. UCT, PD University of Wuppertal, PhD Math., Diploma Math. Books (Wiley): (A) Monte Carlo Frameworks in C++ (B) Financial Modelling – Theory, Implementation and Practice with Matlab Code, (Palgrave McMillan) (C) Interest Rate Derivatives Explained – Part I

Workshop Schedule: 09:00 – 17:30

Break: 10:30 – 11:00
Lunch: 12:30 – 13:30
Break: 15:15 – 15:30

  • Discount Structure
  • Early bird discount
    20% until August 2nd 2019

  • Early bird discount
    10% until September 20th 2019

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

  • Conference + Workshop
    £300 Discount

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

Event Email Reminder

Error