Towards Realistic Financial Time Series Generation via Generative Adversarial Learning

Training network models to accurately respond to market fluctuations requires access to vast amounts of data. Data availability is strictly bound to the market's evolution, which updates only on a daily basis. In this paper, we propose several solutions based on Generative Adversarial Networks...

Full description

Saved in:
Bibliographic Details
Published in2021 29th European Signal Processing Conference (EUSIPCO) pp. 1341 - 1345
Main Authors Dogariu, Mihai, Stefan, Liviu-Daniel, Boteanu, Bogdan Andrei, Lamba, Claudiu, Ionescu, Bogdan
Format Conference Proceeding
LanguageEnglish
Published EURASIP 23.08.2021
Subjects
adversarial
Europe
financial
fintech
Fluctuations
GAN
generation
Generative adversarial networks
Measurement
Signal processing
time series
Time series analysis
Training
Online AccessGet full text

Cover

More Information
Summary:Training network models to accurately respond to market fluctuations requires access to vast amounts of data. Data availability is strictly bound to the market's evolution, which updates only on a daily basis. In this paper, we propose several solutions based on Generative Adversarial Networks for providing artificially generated time series data with realistic properties. The main challenge here is the specificity of the target data, which has properties that are difficult to control and have wide variations in time, e.g., central moment statistics, autocorrelation or cluster volatility. Another contribution is in assessing the quality of synthetic data, in general, as there is no standard metric for this. Experimental validation is carried out on real-world financial data retrieved from the US stock market.
ISSN:2076-1465
DOI:10.23919/EUSIPCO54536.2021.9616176