Deep arbitrage-free learning in a generalized HJM framework via arbitrage-regularization


Loading...

Date

2020-06

Publication Type

Journal Article

ETH Bibliography

yes

Citations

Altmetric

Data

Abstract

A regularization approach to model selection, within a generalized HJM framework, is introduced, which learns the closest arbitrage-free model to a prespecified factor model. This optimization problem is represented as the limit of a one-parameter family of computationally tractable penalized model selection tasks. General theoretical results are derived and then specialized to affine term-structure models where new types of arbitrage-free machine learning models for the forward-rate curve are estimated numerically and compared to classical short-rate and the dynamic Nelson-Siegel factor models.

Publication status

published

Editor

Book title

Journal / series

Volume

8 (2)

Pages / Article No.

40

Publisher

MDPI

Event

Edition / version

Methods

Software

Geographic location

Date collected

Date created

Subject

arbitrage-regularization; bond pricing; model selection; deep learning; dynamic PCA

Organisational unit

03845 - Teichmann, Josef / Teichmann, Josef check_circle

Notes

Funding

Related publications and datasets