Quant GANs: deep generation of financial time series. Issue 9 (1st September 2020)

• Record Type: Journal Article
• Authors: Wiese, Magnus; Knobloch, Robert; Korn, Ralf; Kretschmer, Peter
• Is Part Of: Quantitative finance. Volume 20:Issue 9(2020)
• Page Start: 1419
• Page End: 1440
• Publication Date: 2020-09-01
• Subjects: Financial modeling -- Generative adversarial networks -- Machine learning -- Risk neutral simulation -- Temporal convolutional networks -- Time series; C45 -- C63; Finance -- Periodicals; Business mathematics -- Periodicals; Finance -- Mathematical models -- Periodicals; Investments -- Mathematics -- Periodicals; Economics -- Periodicals; Finances -- Modèles mathématiques -- Périodiques; 332.015118
• DOI: 10.1080/14697688.2020.1730426
• Languages: English
• ISSNs: 1469-7688

Abstract

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.