Javascript Menu by
World Business Strategies Logo

 08:30: Morning Welcome Coffee

09.00 - 09.45: Keynote Speech

Presenter: Vacslav Glukhov, PhD: Executive Director, Linear Quantitative Research, Global Equities, J.P. Morgan (To be confirmed)

Topics in Self-Learning Agents and Traditional Quantitative Models in Finance  

  • What can we draw from our experience of training and running an industry first self-learning agent for electronic order execution?
  • Will traditional hand-crafted heuristic- and quant-based execution algorithms go extinct within 10 years?
  • Does the success of ML and AI agents in finance indicate the eventual demise of traditional quantitative models?
  • Practical aspects of using feeder models and heuristics in AI agents for trading applications.
  • Do we have practical solutions for the equivalence puzzle in Neural Nets

 09.45 - 10.30: XVA, AAD, Intial Margin & FRTB Panel:  


  • To be confirmed


  • Alexandre Antonov: Director, Standard Chartered Bank
  • Andrew Mcclelland: Director, Quantitative Research, Numerix
  • Ignacio Ruiz: Founder & CEO, MoCaX Intelligence
  • Gilles Artaud: Market and Counterparty Risk, Credit Agricole-CIB
  • Assad Bouayoun: Director, XVA Senior Quant, Scotiabank


  • 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 

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?

10.30 – 11.00: Morning Break and Networking Opportunities

11.00 - 11.45: 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 

11.45 - 12.30: Efficient CVA Capital for Collateralised Counterparties

  • Short summary of new CVA Capital rules 
  • Challenges of collateralised CVA with Initial Margin 
    • Forward Initial Margin 
      • Settlement risk & dynamic dates 
  • CVA sensitivities Case study for SA-CVA sensitivities 
    • Finite difference and AAD

Presenter: Justin Chan: Quantitative Strategy, Adaptiv, FIS

Lunch: 12.30 - 13.30

13.30 - 14.15: Deep Primal-Dual Algorithm for BSDEs: Application of Machine Learning to CVA and IM 

Presenter: Pierre Henry-Labordere: Quant, Global Markets Quantitative Research, Société Générale (to be confirmed) 

14.15 - 15.00: Johnson Distributions in Finance - Applications to Dynamic Initial Margin Estimation (JLSMC Method)  

The estimation of dynamic initial margin (DIM) for general portfolios is a challenging problem. We consider different approaches and present a new approach, based on regression, that uses Johnson-type distributions, which are fitted to conditional moments estimated using least-squares Monte Carlo simulation (the JLSMC approach). This approach is compared to DIM estimates computed using nested Monte Carlo as a benchmark. Under a number of test cases, the two approaches are shown to be coherent. Furthermore, we show that estimates of DIM produced under the standard regression approach, which assumes portfolio changes are Gaussian, diverges significantly from the better estimates using the JLSMC and nested Monte Carlo approaches. The standard approach performs particularly poorly if the portfolio changes are far from Gaussian (e.g. for options). To further demonstrate the efficacy of the JLSMC approach we provide illustrative examples using Heston and Hull-White models for different derivatives such as European calls and puts as well as payer and receiver swaptions. 

A further advantage of the new approach is that it only relies on the quantities required for any exposure or XVA calculation. 

  • Dynamic Initial Margin and Methods for its Calculation
  • Monte Carlo Simulation and Least Squares Regression
  • Johnson Distributions
  • The JLSMC Method
  • Backtesting / Benchmarking 

Presenter: Jörg Kienitz: Partner & Nikolai Nowaczyk: Consultant, Quaternion Risk Management

15.00 – 15.20: Afternoon Break and Networking Opportunities

15.20 - 16.15: Closing Presentation 

Examining Real Possibilities and Applications of Distributed Ledger Technologies 

  • Which applications are game changing for finance and why?

Presenter: Massimo Morini: Head of Interest Rate and Credit Models, Banca IMI 

  End of Conference