Historical calibration of SVJD models with deep learning

20 Pages Posted: 8 Dec 2023

See all articles by Milan Fičura

Milan Fičura

University of Economics, Prague - Faculty of Finance and Accounting

Jiri Witzany

University of Economics in Prague

Date Written: December 1, 2023

Abstract

We propose how deep neural networks can be used to calibrate the parameters of Stochastic-Volatility Jump-Diffusion (SVJD) models to historical asset return time series. 1-Dimensional Convolutional Neural Networks (1D-CNN) are used for that purpose. The accuracy of the deep learning approach is compared with machine learning methods based on shallow neural networks and hand-crafted features, and with commonly used statistical approaches such as MCMC and approximate MLE. The deep learning approach is found to be accurate and robust, outperforming the other approaches in simulation tests. The main advantage of the deep learning approach is that it is fully generic and can be applied to any SVJD model from which simulations can be drawn. An additional advantage is the speed of the deep learning approach in situations when the parameter estimation needs to be repeated on new data. The trained neural network can be in these situations used to estimate the SVJD model parameters almost instantaneously.

Keywords: Stochastic volatility, price jumps, SVJD, neural networks, deep learning, CNN

JEL Classification: C15, C22, C45, C58, C63

Suggested Citation

Fičura, Milan and Witzany, Jiri, Historical calibration of SVJD models with deep learning (December 1, 2023). Available at SSRN: https://ssrn.com/abstract=4650097 or http://dx.doi.org/10.2139/ssrn.4650097

Milan Fičura (Contact Author)

University of Economics, Prague - Faculty of Finance and Accounting ( email )

VŠE v Praze
Nám. W. Churchilla 4
130 67
Czech Republic

Jiri Witzany

University of Economics in Prague ( email )

Winston Churchilla Sq. 4
Prague 3, 130 67
Czech Republic

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
67
Abstract Views
2,458
Rank
632,739
PlumX Metrics