Hedging with Neural Networks

31 Pages Posted: 14 May 2020 Last revised: 26 May 2020

See all articles by Johannes Ruf

Johannes Ruf

London School of Economics & Political Science (LSE) - London School of Economics

Weiguan Wang

London School of Economics & Political Science (LSE) - Department of Mathematics

Date Written: May 25, 2020

Abstract

We study neural networks as nonparametric estimation tools for the hedging of options. To this end, we design a network, named HedgeNet, that directly outputs a hedging strategy. This network is trained to minimise the hedging error instead of the pricing error. Applied to end-of-day and tick prices of S&P 500 and Euro Stoxx 50 options, the network is able to reduce the mean squared hedging error of the Black-Scholes benchmark significantly. We illustrate, however, that a similar benefit arises by simple linear regressions that incorporate the leverage effect. Finally, we show how a faulty training/test data split, possibly along with an additional ‘tagging’ of data, leads to a significant overestimation of the outperformance of neural networks.

Keywords: Benchmarking, Black-Scholes, Data leakage, Delta-vega hedging, Hedging error, Linear regression, Neural network, Statistical hedging

JEL Classification: G13, C45

Suggested Citation

Ruf, Johannes and Wang, Weiguan, Hedging with Neural Networks (May 25, 2020). Available at SSRN: https://ssrn.com/abstract=3580132 or http://dx.doi.org/10.2139/ssrn.3580132

Johannes Ruf

London School of Economics & Political Science (LSE) - London School of Economics ( email )

United Kingdom

Weiguan Wang (Contact Author)

London School of Economics & Political Science (LSE) - Department of Mathematics ( email )

Houghton Street
GB-London WC2A 2AE
United Kingdom

Here is the Coronavirus
related research on SSRN

Paper statistics

Downloads
136
Abstract Views
618
rank
229,063
PlumX Metrics