World Business StrategiesServing the Global Financial Community since 2000

Wednesday 18th March 2020

08.00 - 09.00
Registration and Morning Welcome Coffee
09.00 - 09.45
“Reinforcement Learning for xVA hedging”.

Ivan Zhdankin:

Systematic Trading, JPMorgan Chase & Co

09.45 - 10.30
Marginal KVA via Mathematical Programming and Reinforcement Learning

Chris Kenyon:

Director: Head of XVA Quant Modelling, MUFG Securities EMEA plc

10.30 - 11.00
Morning Break and Networking Opportunities
11.00 - 11.45
Model Validation of XVAs with Variation and Initial Margins
  • Pricing and calibration under multicurve G2++ with time dependent volatility
  • Collateral simulation: variation margin and initial margin under ISDA SIMM.
  • Computing exposure and XVAs for swaps and swaptions with variation and initial margin.
  • Sensitivity analysis of model parameters

Abstract

In the last few years initial margin broke into the world of OTC transactions, required both by Central Counterparties and by current regulations of bilateral transactions to neutralize counterparty default risk. In particular, OTC derivatives between market counterparties are subject to the ISDA Standard Initial Margin Model (SIMM).

In our work we use a multicurve two factor Hull-White (G2++) model to compute exposures and XVA figures including variation and initial margins. We test both linear and optional instruments, i.e. IRS and Swaptions, and we assess the detailed effects of tuning several simulation parameters: collateral thresholds, minimum transfer amount, time simulation steps, Monte Carlo scenarios, interpolation schemes, etc. We show that there exist optimal parameters values leading to accurate and stable results in a reasonable computational time.

Marco Bianchetti:

Head of Market and Counterparty Risk IMA Methodologies, Intesa Sanpaolo

Marco Scaringi:

Quantitative Analyst, Risk Management, Intesa Sanpaolo

11.45 - 12.30
Machine Learning + Chebyshev techniques for XVA: boosting each other"

The computation of risk metrics poses a huge computational challenge to banks. Many different techniques have been developed and implemented in the last few years to try and tackle the problem. We focus on Chebyshev tensors enhanced by machine learning, showing why they are such powerful pricing approximators  in risk calculations. We show how the presented unique mix of techniques can be applied in different calculations. We illustrate with Numerical results in Counterparty Credit Risk and Dynamic initial Margin. In particular, We will give special attention on how to side-step the curse of dimensionality and how machine learning techniques can be used to boost Chebyshev tensors.

Mariano Zeron:

Head of Research and Development: MoCaX Intelligence

12.30 - 13.30
Lunch
13.30 - 14.15
Bayesian and Machine Learning Approaches to XVA Integration

Andrew Green: 

Managing Director and Lead GFI Quant, Scotiabank
14.15 - 15.00
Derivatives Pricing with A Deep Learning Approach

Youssef Elouerkhaoui:

Managing Director, Global Head of Markets Quantitative Analysis, Citi

15.00 - 15.30
Afternoon Break and Networking Opportunities
15.30 - 16.15
Balance Sheet XVA by Deep Learning and GPU

Stéphane Crépey:

Professor of Mathematics Université de Paris, Laboratoire de Probabilités, Statistique et Modélisation

16.15 - 17.00
The Impact of Initial Margin on Derivatives Pricing with an Application of Machine Learning

Presenter to be confirmed

17.00 - 17.45
XVA, FRTB & Machine Learning Panel

Topics: 

XVA & Initial Margin

  • Initial Margin, a push for more model standardization? Good or bad?
  • How do you interpret the regulatory requirements to validate and monitor SIMM, and how would a firm best go about meeting those requirements?
  • SIMM relies on counterparts calculating their own sensitivities. Do the panelists foresee that causing any problems meeting requirements or additional costs?
  • Discuss Implementing SIMM for Non Cleared Initial Margin Rules
  • Discuss the role of technology to increase the knowledge base from XVA calculations

Machine Learning  

  • Discuss the existing applications of machine learning in XVA
  • Discuss the potential new applications of machine learning in XVA going forward
  • How important is machine learning in calculation of XVAs?
  • Best practices to incorporate machine learning across XVAs
  • Is machine learning necessary for XVA?

Discuss the Impact of FRTB on XVA’s 

  • How will the latest proposed regulations impact CVA calculations
  • Review what are the most important factors to take into account when calculating the new CVA
  • Calculating & Implementing FRTB CVA. How will it affect banks’ internal modelling for counterparty risk and risk management?

Moderator:

 

Ivan Zhdankin:

Systematic Trading, JPMorgan Chase & Co

Sarah B Tremel:

Global Head of Analytics – Product Control, HSBC

Jon Gregory: 

Independent xVA Expert

Andrew Green: 

Managing Director and Lead GFI Quant, Scotiabank

Ignacio Ruiz:

MoCaX Intelligence
  • Discount Structure
  • 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

Also attend