MTSS-GAN: Multivariate Time Series Simulation Generative Adversarial Networks

7 Pages Posted: 26 Jun 2020

See all articles by Derek Snow

Derek Snow

The Alan Turing Institute; New York University (NYU) - Finance and Risk Engineering Department; University of Auckland

Date Written: June 2, 2020

Abstract

MTSS-GAN is a new generative adversarial network (GAN) developed to simulate diverse multivariate time series (MTS) data with finance applications in mind. The purpose of this synthesiser is two-fold, we both want to generate data that accurately represents the original data, while also having the flexibility to generate data with novel and unique relationships that could help with model testing and robustness checks. The method is inspired by stacked GANs originally designed for image generation. Stacked GANs have produced some of the best quality images, for that reason MTSS-GAN is expected to be a leading contender in multivariate time series generation.

Keywords: Time Series, Generation, Synthetic, GAN, Generative, Multivariate, Simulation, Synthesiser

JEL Classification: C6, G12, C22

Suggested Citation

Snow, Derek, MTSS-GAN: Multivariate Time Series Simulation Generative Adversarial Networks (June 2, 2020). Available at SSRN: https://ssrn.com/abstract=3616557 or http://dx.doi.org/10.2139/ssrn.3616557

Derek Snow (Contact Author)

The Alan Turing Institute ( email )

British Library, 96 Euston Rd
London, NW1 2DB
United Kingdom

HOME PAGE: http://https://www.turing.ac.uk/

New York University (NYU) - Finance and Risk Engineering Department ( email )

6 Metrotech Center
New York, NY 11201
United States

University of Auckland ( email )

Private Bag 92019
Auckland Mail Centre
Auckland, 1142
New Zealand

Here is the Coronavirus
related research on SSRN

Paper statistics

Downloads
668
Abstract Views
1,813
rank
43,762
PlumX Metrics