Publication type: Article in scientific journal
Type of review: Peer review (publication)
Title: Tackling the exponential scaling of signature-based generative adversarial networks for high-dimensional financial time-series generation
Authors: De Meer Pardo, Fernando
Schwendner, Peter
Wunsch, Marcus
et. al: No
DOI: 10.3905/jfds.2022.1.109
Published in: The Journal of Financial Data Science
Volume(Issue): 4
Issue: 4
Page(s): 110
Pages to: 132
Issue Date: 2022
Publisher / Ed. Institution: Portfolio Management Research
ISSN: 2640-3943
2640-3951
Language: English
Subjects: GAN; Hierarchial clustering; Overfitting; Portfolio construction
Subject (DDC): 332: Financial economics
Abstract: Generative adversarial networks (GANs) have been shown to be able to generate samples of complex financial time series, particularly by employing the concept of path signatures, a universal description of the geometric properties of a data stream whose expected value uniquely characterizes the time series. Specifically, the SigCWGAN model (Ni et al. 2020) can generate time series of arbitrary length; however, the parameters of the neural network employed grow exponentially with the dimension of the underlying time series, which makes the model intractable when seeking to generate large financial market scenarios. To overcome this problem of dimensionality, the authors propose an iterative generation procedure relying on the concept of hierarchies in financial markets. The authors construct an ensemble of GANs that they call the Hierarchical-SigCWGAN, which is based on hierarchical clustering that approximates signatures in the spirit of the original model. The Hierarchical-SigCWGAN can scale to higher dimensions and generate large-dimensional scenarios in which the joint behavior of all the assets in the market is replicated. The model is validated by comparing its performance on a series of similarity metrics with respect to the original SigCWGAN on a dataset in which it is still tractable and by showing its scalability on a larger dataset.
URI: https://digitalcollection.zhaw.ch/handle/11475/23562
License (according to publishing contract): Licence according to publishing contract
Departement: School of Engineering
School of Management and Law
Organisational Unit: Institute of Data Analysis and Process Design (IDP)
Institute of Wealth & Asset Management (IWA)
Appears in collections:Publikationen School of Engineering
Publikationen School of Management and Law

Files in This Item:
There are no files associated with this item.


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.