Generation of Synthetic Financial Time Series with GANs - Casper Hogenboom

Показать описание

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.

ING Analytics

Рекомендации по теме

Комментарии

Really nice work! Thanks for uploading your presentation, you gave me very useful insights for my PhD thesis. Greetings from Brazil :)

aehauehaue

Can you share the code which is related to 1D GAN on sequence data or biological sequence data?Thanks

mramzanshahidkhan

Nice work, what do you think if WGAN is similar to Reinforcement learning (like Actor-Critic for ex) or Policy gradient optimization problems ?

SuperSambram

could you share the 2D-GAN related code for generating synthetic sequence data?many thanks

MargaretXu-bl

hey, thanks for the video... Do you have github link for these codes...? I'll be grateful to you for this...

SurbhiGupta-ijwd

Can you help me in understanding how the condition passed in the generator impacts the generator output?

Also, do features passed in the condition have a one to one correspondence with the output of the generator? For instance if 20 features are passed as condition in the generator, and the generator is made to produce an output of 20 features, will the features in the condition have a one to one correspondence with the generated features output?

hajrawaheed

Do you have the source code available?

KhayamGondal

Generation of Synthetic Financial Time Series with GANs - Casper Hogenboom

Generation of Synthetic Financial Time Series with GANs - Casper Hogenboom

What is Synthetic Data? No, It's Not 'Fake' Data

Generate Synthetic Time series Data with Open source Tools

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

Synthetic Financial Data Generation with MlFinLab

GenAI Financial Synthetic Data Generator [Mimic Your Data] | LLM + RAG [ Zypher 7B LLM ] Mistral LLM

Stamatis Lykos & Elena Chatzimichali - Synthetic Data in Financial Time Series | PyData London 2...

AI Cafe Realistic Financial Time Series Generation

GANs in Finance

Synthetic Data Generation of Financial Transactions

What is Time Series Analysis?

Master Class: GANS with Applications in Synthetic Data Generation in Quantitative Finance

Synthetic data generation with CTGAN

QU Fall School | Synthetic Data Generation in Finance

Financial Time Series Modelling Using Generative Models

#6 | OpenBDLM Tutorial | How to generate synthetic time series

QU Fall School | Synthetic Data Generation in Finance

GANs for Tabular Synthetic Data Generation (7.5)

Synthetic DATA Generation using LANGCHAIN 🦜️🔗

Synthetic Data Generation using LLM: Crash Course for Beginners

QU Fall School | GANS with Applications in Synthetic Data Generation in Quantitative Finance

How to Make Synthetic Data | Synthetic Data Generation for Machine Learning

GANs in Finance: Exploring the Revolution in Predictive Modeling

Multivariate Time Series Synthesis Using Generative Adversarial Networks