This workshop is complimentary to all conference attendees.

Machine Learning Models for the Interest Rates

Session One: Machine Learning Architecture (VAE, VEGD) – 13:30 to 15:00

• Variational autoencoder architecture (VAE)
  • The roles of encoder and decoder, latent space
  • Deliberately introducing uncertainty in reconstruction
  • Loss function and optimization loop
  • Reconstruction with VAE
  • Generation with VAE
• Variational encoder-generator-decoder architecture (VEGD)
  • The role of generator between encoder and decoder
  • Generator parameterization
  • Generator training
• Hands-on examples with Python
  • VAE for handwritten digits from the MNIST dataset
  • VEGD for arithmetic on handwritten digits from the MNIST dataset

Coffee Break – 15:00 to 15:30

Session Two: Application to Interest Rate Models – 15:30 to 17:00

• Principles of interest rate model construction
  • Stochastic drivers and state variables
  • Historical calibration in P-measure
  • Arbitrage-free calibration in Q-measure
  • Three types of interest rate models and connection between them
• One factor short rate models
  • SDE models: HW, BK, CIR++
  • Machine learning (VEGD) models
• Two factor short rate models
  • SDE models: HW2F/G2, CIR2++
  • Machine learning (VEGD) models
• Forward rate models
  • Single rate SDE models: Black, SABR
  • Forward curve SDE models: HJM, LMM, SABR-LMM
  • Machine learning (VEGD) models
• Curve basis models
  • Static models: Nelson-Siegel (NS), Nelson-Siegel-Svensson (NSS)
  • SDE models: AFNS, Factor HJM
  • Machine learning (VAE) counterparts of static models
  • Machine learning (VEGD) counterparts of SDE models
• Hands-on examples with Python
  • VAE for the yield curve with one and two dimensional latent space
  • Historical VEGD model training in P-measure
  • Arbitrage-free market implied VEGD model calibration in Q-measure

Q&A – 17:00 to 17:30

Alexander Sokol:

Executive Chairman and Head of Quant Research, CompatibL

Alexander Sokol: Executive Chairman and Head of Quant Research, CompatibL

Alexander Sokol is the founder, Executive Chairman, and Head of Quant Research at CompatibL, a trading and risk technology company. He is also the co-founder of Numerix, where he served as CTO from 1996 to 2003, and the co-founder of Duality Group, where he served as CTO from 2017 to 2020.

Alexander won the Quant of the Year Award in 2018 together with Leif Andersen and Michael Pykhtin, for their joint work revealing the true scale of the settlement gap risk that remains even in the presence of initial margin. Alexander’s other notable research contributions include systemic wrong-way risk (with Michael Pykhtin, Risk Magazine), joint measure models, and the local price of risk (with John Hull and Alan White, Risk Magazine), and mean reversion skew (Risk Books, 2014).

Alexander earned his BA from the Moscow Institute of Physics and Technology at the age of 18, and a PhD from the L. D. Landau Institute for Theoretical Physics at the age of 22. He was the winner of the USSR Academy of Sciences Medal for Best Student Research of the Year in 1988.