Machine Learning for Multiple Yield Curve Markets: Fast Calibration in the Gaussian Affine Framework

20 Pages Posted: 12 May 2020

See all articles by Sandrine Gümbel

Sandrine Gümbel

University of Freiburg - Institut für Mathematische Stochastik

Thorsten Schmidt

University of Freiburg

Date Written: April 17, 2020

Abstract

Calibration is a highly challenging task, in particular in multiple yield curve markets. This paper is a first attempt to study the chances and challenges of the application of machine learning techniques for this. We employ Gaussian process regression, a machine learning methodology having many similarities with extended Kalman filtering - a technique which has been applied many times to interest rate markets and term structure models.

We find very good results for the single curve markets and many challenges for the multi curve markets in a Vasicek framework. The Gaussian process regression is implemented with the Adam optimizer and the non-linear conjugate gradient method, where the latter performs best. We also point towards future research.

Keywords: Vasicek model, single curve markets, affine models, multi curve markets, machine learning, Gaussian process regression, filtering, Adam optimizer, conjugate gradient method, term structure models

Suggested Citation

Gümbel, Sandrine and Schmidt, Thorsten, Machine Learning for Multiple Yield Curve Markets: Fast Calibration in the Gaussian Affine Framework (April 17, 2020). Available at SSRN: https://ssrn.com/abstract=3578604 or http://dx.doi.org/10.2139/ssrn.3578604

Sandrine Gümbel

University of Freiburg - Institut für Mathematische Stochastik ( email )

D-79104, Freiburg
Germany

Thorsten Schmidt (Contact Author)

University of Freiburg ( email )

Fahnenbergplatz
Freiburg, D-79085
Germany

Do you have negative results from your research you’d like to share?

Paper statistics

Downloads
86
Abstract Views
501
Rank
527,956
PlumX Metrics