Machine Learning Models for the Interest Rates: 13.30 – 17.30

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