Deep Smoothing of the Implied Volatility Surface

16 Pages Posted: 20 Jun 2019

See all articles by Damien Ackerer

Damien Ackerer

Swissquote Bank

Natasa Tagasovska

University of Lausanne

Thibault Vatter

Columbia University - Departments of Statistics and Mathematics; University of Lausanne - School of Economics and Business Administration (HEC-Lausanne)

Date Written: May 23, 2019

Abstract

We present an artificial neural network (ANN) approach to value financial derivatives. Atypically to standard ANN applications, practitioners equally use option pricing models to validate market prices and to infer unobserved prices. Importantly, models need to generate realistic arbitrage-free prices, meaning that no option portfolio can lead to risk-free profits. The absence of arbitrage opportunities is guaranteed by penalizing the loss using soft constraints on an extended grid of input values. ANNs can be pre-trained by first calibrating a standard option pricing model, and then training an ANN to a larger synthetic dataset generated from the calibrated model. The parameters transfer as well as the non-arbitrage constraints appear to be particularly useful when only sparse or erroneous data are available. We also explore how deeper ANNs improve over shallower ones, as well as other properties of the network architecture. We benchmark our method against standard option pricing models, such as Heston with and without jumps. We validate our method both on training sets, and testing sets, namely, highlighting both their capacity to reproduce observed prices and predict new ones.

Suggested Citation

Ackerer, Damien and Tagasovska, Natasa and Vatter, Thibault, Deep Smoothing of the Implied Volatility Surface (May 23, 2019). Available at SSRN: https://ssrn.com/abstract=3402942 or http://dx.doi.org/10.2139/ssrn.3402942

Damien Ackerer (Contact Author)

Swissquote Bank ( email )

Ch. de la Crétaux 33
Gland, Vaud 1196
Switzerland

Natasa Tagasovska

University of Lausanne ( email )

France

Thibault Vatter

Columbia University - Departments of Statistics and Mathematics ( email )

1255 Amsterdam Avenue
New York, NY 10027
United States

University of Lausanne - School of Economics and Business Administration (HEC-Lausanne) ( email )

Lausanne, 1015
Switzerland

Register to save articles to
your library

Register

Paper statistics

Downloads
31
Abstract Views
133
PlumX Metrics