Can Generative Adversarial Networks (GANs) forecast financial time-series data? Milena Vuletić Postgraduate Student at the Oxford-Man Institute of Quantitative Finance shares her research findings.
Can Generative Adversarial Networks (GANs) forecast financial time-series data? Milena Vuletić Postgraduate Student at the Oxford-Man Institute of Quantitative Finance shares her research findings.
July 2023
Fin-GAN: Forecasting and Classifying Financial Time Series via Generative Adversarial Networks
Vuletić, Milena and Cucuringu, Mihai and Prenzel, Felix
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.
You are now exiting our website
Please be aware that you are now exiting the Man Institute | Man Group website. Links to our social media pages are provided only as a reference and courtesy to our users. Man Institute | Man Group has no control over such pages, does not recommend or endorse any opinions or non-Man Institute | Man Group related information or content of such sites and makes no warranties as to their content. Man Institute | Man Group assumes no liability for non Man Institute | Man Group related information contained in social media pages. Please note that the social media sites may have different terms of use, privacy and/or security policy from Man Institute | Man Group.