Generation of Synthetic Financial Time Series with GANs - Casper Hogenboom
During his master thesis research, Casper has been working on financial time-series generation with use of Generative Adversarial Networks (GANs). The unparalleled success of GANs in generating realistic synthetic images has initiated an entirely new field of research. However, due to the inherent difficulty of evaluating synthetic generated data instances, this progress has been largely limited to applications like images and video, where visual inspection can serve as a guide. In this research, we will extend state-of-the-art concepts within GAN training to the (financial) time series domain. The challenging task is to evaluate the synthetically generated time-series, which need to have statistical properties as close as possible to the historic data. This talk will give an insight into difficulties encountered during this research, and discuss the proposed solutions.
Видео Generation of Synthetic Financial Time Series with GANs - Casper Hogenboom канала ING WBAA
Видео Generation of Synthetic Financial Time Series with GANs - Casper Hogenboom канала ING WBAA
Показать
Комментарии отсутствуют
Информация о видео
Другие видео канала
QuantUniversity Summer School 2020 | Generating Synthetic Data with (GANs)UX meetup 2021 - Jan Williem - From Data to Visualization with IntentNIPS 2016 Workshop on Adversarial Training - Soumith Chintala - How to train a GANThe secrets of learning a new language | Lýdia Machová[Classic] Generative Adversarial Networks (Paper Explained)ING Data Science MeetupFortune-Telling with Python: An Intro to Facebook Prophet1D Convolutional Neural Networks for Time Series Modeling - Nathan Janos, Jeff RoachA Friendly Introduction to Generative Adversarial Networks (GANs)Time Series Data Augmentation for Neural Networks by Time Warping with Discrimination | ICPR - 2020UX meetup WBAAUnderstand the Math and Theory of GANs in ~ 10 minutesTime to Event Analysis A Pedestrian Approach” - Ilan Fridman RojasHow to Make Synthetic Data | Synthetic Data Generation for Machine LearningGenerative Adversarial Networks (GANs) - ComputerphileTheory and Algorithms for Forecasting Non-Stationary Time Series (NIPS 2016 tutorial)Ian Goodfellow: Generative Adversarial Networks (NIPS 2016 tutorial)WGAN implementation from scratch (with gradient penalty)TadGAN: Time Series Anomaly Detection Using Generative Adversarial NetworksExperienceAI: GAN for Time Series Data Augmentation in Astronomy - Pavlos Protopapas, Harvard U