Fin-GAN: Forecasting and Classifying Financial Time Series via Generative Adversarial Networks

34 Pages Posted: 19 Jan 2023 Last revised: 24 May 2023

See all articles by Milena Vuletić

Milena Vuletić

University of Oxford

Mihai Cucuringu

University of Oxford - Department of Statistics

Felix Prenzel

University of Oxford - Mathematical Institute

Date Written: January 18, 2023

Abstract

We investigate the use of Generative Adversarial Networks (GANs) for probabilistic forecasting of financial time series. To this end, we introduce a novel economics-driven loss function for the generator. This newly designed loss function renders GANs more suitable for a classification task, and places them into a supervised learning setting, whilst producing full conditional probability distributions of price returns given previous historical values. Our approach moves beyond the point estimates traditionally employed in the forecasting literature, and allows for uncertainty estimates. Numerical experiments on equity data showcase the effectiveness of our proposed methodology, which achieves higher Sharpe Ratios compared to classical supervised learning models, such as LSTMs and ARIMA.

Keywords: GANs, financial returns, time series forecasting, classification

JEL Classification: G17, C15, C22, C32, C45, C53

Suggested Citation

Vuletić, Milena and Cucuringu, Mihai and Prenzel, Felix, Fin-GAN: Forecasting and Classifying Financial Time Series via Generative Adversarial Networks (January 18, 2023). Available at SSRN: https://ssrn.com/abstract=4328302 or http://dx.doi.org/10.2139/ssrn.4328302

Milena Vuletić (Contact Author)

University of Oxford ( email )

Radcliffe Observatory, Andrew Wiles Building
Woodstock Rd
Oxford, Oxfordshire OX2 6GG
United Kingdom

Mihai Cucuringu

University of Oxford - Department of Statistics ( email )

24-29 St Giles
Oxford
United Kingdom

Felix Prenzel

University of Oxford - Mathematical Institute ( email )

Radcliffe Observatory, Andrew Wiles Building
Woodstock Rd
Oxford, Oxfordshire OX2 6GG
United Kingdom

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
1,582
Abstract Views
3,202
Rank
18,785
PlumX Metrics