Autoencoder Market Models for Interest Rates

Today’s faster processors and cloud computing create new opportunities for the adoption of more realistic machine learning models. Download the presentation to learn more about variational autoencoders (VAEs) and autoencoder market models (AEMMs) and how they perform against some of the fastest numerical methods.

Workshop Materials

Today, the performance of pre-trained machine learning models is comparable to some of the fastest numerical methods. Moreover, neural networks easily outperform classical regression techniques such as principal component analysis (PCA) in representing historical interest rate curve shapes and their evolution. They also have the potential to surpass classical curve basis methods such as the Nelson– Siegel (NS) basis and its extension, the Nelson–Siegel–Svensson (NSS) basis.

In this presentation, we focus on the architecture of VAEs and AEMMs, explain how they work, and provide hands-on examples.

VAE architecture:

The roles of an encoder and a decoder
Deliberately introducing uncertainty in a reconstruction
The loss function and optimization loop
Reconstruction and generation with a VAE

VAE for the yield curve:

Curve representation
Training on historical data
One-hot encoding of currency
VAE with a dimensional latent space
VAE with a separable two-dimensional latent space
VAE with a non-separable two-dimensional latent space
Comparison to the NS and NSS bases

Hands-on examples in Python:

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

Author

Alexander Sokol

Alexander Sokol is the founder, Executive Chairman, and Head of Quant Research at CompatibL.

In 2022, Alexander was awarded the Fintech Person of the Year Award for his expertise and developments on a new class of machine learning risk models that can work with short pandemic-era historical time series. In 2018 Alexander won the Quant of the Year Award, 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).