Quant GANs: deep generation of financial time series

DOI10.1080/14697688.2020.1730426zbMath1454.91366arXiv1907.06673OpenAlexW3103346379MaRDI QIDQ5139243

Ralf Korn, Peter Kretschmer, Magnus Wiese, Robert Knobloch

Publication date: 7 December 2020

Published in: Quantitative Finance (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1907.06673

zbMATH Keywords

time seriesmachine learningfinancial modelinggenerative adversarial networkstemporal convolutional networksrisk neutral simulation

Mathematics Subject Classification ID

Time series, auto-correlation, regression, etc. in statistics (GARCH) (62M10) Statistical methods; risk measures (91G70) Financial applications of other theories (91G80)

Related Items (18)

Robust utility maximization under model uncertainty via a penalization approach ⋮ QuantGAN ⋮ A generative model for fBm with deep ReLU neural networks ⋮ Distributionally robust end-to-end portfolio construction ⋮ Monte Carlo simulation of SDEs using GANs ⋮ Estimation of extreme quantiles from heavy-tailed distributions with neural networks ⋮ Continuous and impulse controls differential game in finite horizon with Nash-equilibrium and application ⋮ Generative adversarial networks applied to synthetic financial scenarios generation ⋮ Empirical deep hedging ⋮ Modern AI \textit{versus} century-old mathematical models: how far can we go with generative adversarial networks to reproduce stochastic processes? ⋮ Recent advances in reinforcement learning in finance ⋮ A generative model of a limit order book using recurrent neural networks ⋮ GANs training: A game and stochastic control approach ⋮ Designing universal causal deep learning models: The geometric (Hyper)transformer ⋮ Grouping of contracts in insurance using neural networks ⋮ Generative adversarial networks for financial trading strategies fine-tuning and combination ⋮ Forecasting financial time series with Boltzmann entropy through neural networks ⋮ cCorrGAN: conditional correlation GAN for learning empirical conditional distributions in the elliptope

Uses Software

• SciPy
• PyTorch
• ImageNet
• GitHub
• AlexNet
• WaveNet
• deepAD
• Wasserstein GAN

Cites Work

• Unnamed Item
• The Pricing of Options and Corporate Liabilities
• Generalized autoregressive conditional heteroscedasticity
• Empirical properties of asset returns: stylized facts and statistical issues
• Probability distribution of returns in the Heston model with stochastic volatility*
• Financial Modelling with Jump Processes
• Deep hedging
• A Closed-Form Solution for Options with Stochastic Volatility with Applications to Bond and Currency Options
• Deep optimal stopping
• Optimal Transport

This page was built for publication: Quant GANs: deep generation of financial time series