Quant GANs: Deep Generation of Financial Time Series

Abstract

Modeling financial time series by stochastic processes is a challenging task and a central area of research in financial mathematics. As an alternative, we introduce Quant GANs, a data-driven model which is inspired by the recent success of generative adversarial networks (GANs). Quant GANs consist of a generator and discriminator function, which utilize temporal convolutional networks (TCNs) and thereby achieve to capture long-range dependencies such as the presence of volatility clusters. The generator function is explicitly constructed such that the induced stochastic process allows a transition to its risk-neutral distribution. Our numerical results highlight that distributional properties for small and large lags are in an excellent agreement and dependence properties such as volatility clusters, leverage effects, and serial autocorrelations can be generated by the generator function of Quant GANs, demonstrably in high fidelity.

arXiv commentCorrected typos. Added section 2 as an overview of existing literature. Added section 5.3 to clarify the modeling assumptions. Appendix B now contains more details on the neural network architectures used. Changed latex template

Cited by in corpus (16)

• Modern Machine Learning Tools for Monitoring and Control of Industrial Processes: A Survey
• Conditional Sig-Wasserstein GANs for Time Series Generation
• Robust utility maximization under model uncertainty via a penalization approach
• Continuous and Impulse Controls Differential Game in Finite Horizon with Nash-Equilibrium and Application
• Connecting GANs, MFGs, and OT
• Data-Driven Modeling of Noise Time Series with Convolutional Generative Adversarial Networks
• cCorrGAN: Conditional Correlation GAN for Learning Empirical Conditional Distributions in the Elliptope
• Theoretically Motivated Data Augmentation and Regularization for Portfolio Construction
• SDE approximations of GANs training and its long-run behavior
• If You Like It, GAN It. Probabilistic Multivariate Times Series Forecast With GAN
• Generative modeling of time-dependent densities via optimal transport and projection pursuit
• Quantum generative modeling for financial time series with temporal correlations
• Synthetic Random Environmental Time Series Generation with Similarity Control, Preserving Original Signal's Statistical Characteristics
• Learning to Manage Investment Portfolios beyond Simple Utility Functions
• Diffolio: A Diffusion Model for Multivariate Probabilistic Financial Time-Series Forecasting and Portfolio Construction
• Robust time series generation via Schrödinger Bridge: a comprehensive evaluation