Javascript Menu by
World Business Strategies Logo

XVA, MVA & AAD Stream 

 08:30: Registration and Morning Welcome Coffee 

09.00 – 09.45: Sarah B Tremel: Global Head of Analytics, Global Valuation Group, HSBC Bank 

Keynote: Usage of Machine Learning in Finance 

  • What is Machine Learning
  • Current usage in Finance, e.g. algo trading, fraud, etc
  • Other possible applications in the future
  • How to implement these technics

09.45 - 10.30: ISDA SIMM: Evidenced Based Approach to Governance and Development” 

Presenter: Nnamdi Okaeme: Director - Risk and Capital, International Swaps and Derivatives Association, Inc. (ISDA)

 10.30 – 11.00 Morning Break and Networking Opportunities

11.00 - 11.45: MVA using Machine Learning TechniquesGilles Artaud

  • Initial Margin: why and what?
  • IM Impacts on pricing (on different valuation adjustments
  • Brute force computations; more elaborate techniques: AAD, American Monte Carlo
  • How can Machine Learning help?

Presenter: Gilles Artaud: Market and Counterparty Risk, Credit Agricole-CIB

11.45 - 12.30: Dynamic IM and XVAs via Chebyshev Spectral DecompositionIgnacio Ruiz

  • The power of Chebyshev – MoCaX as a Smart interpolation scheme
  • Selection of interpolating points and functions
  • Chebyshev nodes Chebyshev polynomials in the context of Risk Calculations
  • Theoretical basis: three fundamental theorems
  • Example: Parametric Chebyshev interpolation for Risk Calculations
  • Practical cases studies: CVA, CVA on exotics, Accurate MVA, Ultra-fast XVA sensitivities
  • Commercial benefits: reduction of hardware costs, effective computation of risk metrics, hedging regulatory risk
  • Generic AAD for any pricer via Chebyshev Decomposition  

Presenter: Ignacio Ruiz: Founder & CEO, MoCaX Intelligence

12.30 - 13.30: Lunch

13.30 – 14.15: Accelerated MVA in the Probability Matrix Method

  • Introduction to the Probability Matrix Method
  • Simulating IM using full SIMM and CCP formulas
  • Practical examples and benchmarks
  • Live demo

Presenter: Martin Engblom: Co CEO triCalculate, TriOptima, a NEX Group Company 

14.15 - 15.00: GPU - Accelerated MVA 

  • MVA: a new computational challenge
  • Benefits of a full evaluation: a comparison with less sophisticated approaches
  • Calculating future sensitivities on GPU architecture: Challenges and how to approach

Presenter: To be confirmed

 15.00 - 15.30: Afternoon Break and Networking Opportunities

15.30 - 16.15: KVA from the Beginning Mats Kjaer


We use a single period structural model of a dealer balance sheet to study the impact of regulatory capital requirements on the marginal fair value and shareholder indifference price of a new derivative. As expected the former does not change. The latter is reduced by a capital valuation adjustment, which depends on the financing method used by the dealer. Finally we show that if the dealer hedges the derivative, then the indifference price is related to the cost of setting up the hedge. 

Presenter: Mats Kjaer: Head of Quant XVA Analytics, Bloomberg LP 

16.15 - 17.00: Revisiting KVAAndrew Green

  • Examine the choice of measure: risk-neutral vs. real world
  • Explore the relationship between FVA, KVA and debt and equity financing
  • Relate KVA to corporate finance models

Presenter: Andrew Green: Managing Director and XVA Lead Quant, Scotiabank  

17.00 – 18.00:  Panel


  • Vladimir Chorniy: Senior Technical Lead, BNP Paribas


  • Dong Qu: Managing Director, CVA and Risk Analytics, UniCredit
  • Massimo Morini: Head of Interest Rate and Credit Models, Gruppo Intesa Sanpaolo
  • Ignacio Ruiz: Founder & CEO, MoCaX Intelligence
  • Andrew Green: Managing Director and XVA Lead Quant, Scotiabank  
  • Nnamdi Okaeme: Director - Risk and Capital, International Swaps and Derivatives Association, Inc. (ISDA) 
  • Mats Kjaer: Head of Quant XVA Analytics, Bloomberg LP 


MVA, Intial Margin & SIMM Topics: 

  • 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
  • Explore the interaction between MVA and XVAs:
    • What does MVA mean for XVA overall? Can you simplify the valuation adjustments?
    • Understand the impacts of initial margin, bi-lateral initial margin and MVA on business models
    • Is it possible to ensure transparency of derivative pricing calculation to reduce disputes

XVA & Machine Learning  

  • Discuss the existing and potential applications of machine learning in 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?