Seminar Katedre za verovatnoću i statistiku, 18. april 2023.

Naredni sastanak Seminara Katedre za verovatnoću i statistiku biće održan u utorak, 18. aprila 2023, u sali 840 Matematičkog fakulteta, sa početkom u 17:15 časova.

Predavač: Milena Vuletić (Univerzitet u Oksfordu)

Naslov predavanja: Fin-GAN: FORECASTING AND CLASSIFYING FINANCIAL TIME SERIES VIA GENERATIVE ADVERSARIAL NETWORKS

Abstrakt: 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.

Predavanje je moguće pratiti i onlajn, putem sledećeg linka:

https://zoom.us/j/95910978522?pwd=T2U2aXY2VklHZHh6aiswQTQ2RXREdz09

Meeting ID: 959 1097 8522
Passcode: 451968



Nažalost nije moguće ostaviti komentar.