Free
Complimentary Workshop: Machine Learning Models for the Interest Rates

Complimentary Workshop: Machine Learning Models for the Interest Rates

Actions and Detail Panel

Free

Event Information

Share this event

Date and time

Location

Location

Online event

Event description
Day 1: Variational Autoencoder (VAE) for the Yield Curve & Day 2: Machine Learning Models in Q- and P-Measure

About this event

Machine Learning Models for the Interest Rates

Session One/Day 1: Variational Autoencoder (VAE) for the Yield Curve

Tuesday 7th June: 15.00 - 17.00 BST

VAE architecture

  • The roles of encoder and decoder
  • Deliberately introducing uncertainty in reconstruction
  • Loss function and optimization loop
  • Reconstruction with VAE
  • Generation with VAE

VAE for the yield curve

  • Curve representation
  • Training on historical data
  • One-hot encoding of currency
  • VAE with dimensional latent space
  • VAE with separable two dimensional latent space
  • VAE with non-separable two dimensional latent space
  • Comparison to Nelson-Siegel (NS) and Nelson-Siegel-Svensson (NSS) basis

Hands-on examples with Python

  • VAE for handwritten digits from the MNIST dataset
  • VAE for the yield curve

Session Two/Day 2: Machine Learning Models in Q- and P-Measure

Wednesday 8th June: 15.00 - 17.00 BST

Timing: each session 2 hours with 5 min coffee break.

One factor short rate models

  • Classical time-homogeneous one factor short rate models (Vasicek, CIR, etc.)
  • Classical arbitrage-free one factor short rate models (HW, CIR++, etc.)
  • Autoencoder one factor short rate models in Q- and P-measure
  • Market implied and historical calibration

Two factor short rate models

  • Classical two factor short rate models (HW2F/G2, CIR2++, etc.)
  • Autoencoder two factor short rate models in Q- and P-measure
  • Market implied and historical calibration

Forward rate models

  • Classical forward rate models (HJM, LMM)
  • Autoencoder forward rate models in Q-measure
  • Market implied calibration

Term rate models

  • Classical term rate models (AFNS, Factor HJM)
  • Autoencoder term rate models in P-measure
  • Historical calibration

Hands-on examples with Python

  • Autoencoder short rate model in Q- and P-measure
  • Autoencoder forward rate model in Q-measure
  • Autoencoder term rate model in P-measure

Timing: each session 2 hours with 5 min coffee break.

Presenter: 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.

By registering for this event, attendees consent to receive further email communication on this topic from World Business Strategies Ltd.

Share with friends

Date and time

Location

Online event

Save This Event

Event Saved