Hedging with Neural Networks
Authors:
Preprint
- 19 April 2020
- preprint
- Published by Elsevier in SSRN Electronic Journal
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
All Related Versions
This publication has 16 references indexed in Scilit:
- Regime‐dependent smile‐adjusted delta hedgingJournal of Futures Markets, 2011
- Dynamic Hedging of Portfolio Credit DerivativesSIAM Journal on Financial Mathematics, 2011
- Model-free hedge ratios and scale-invariant modelsJournal of Banking & Finance, 2007
- Delta-hedging vega risk?Quantitative Finance, 2004
- The Focused Information CriterionJournal of the American Statistical Association, 2003
- Pricing and hedging derivative securities with neural networks and a homogeneity hintJournal of Econometrics, 2000
- Uncertain volatility and the risk-free synthesis of derivativesApplied Mathematical Finance, 1995
- A Nonparametric Approach to Pricing and Hedging Derivative Securities Via Learning NetworksThe Journal of Finance, 1994
- A Closed-Form Solution for Options with Stochastic Volatility with Applications to Bond and Currency OptionsThe Review of Financial Studies, 1993
- Discretely adjusted option hedgesJournal of Financial Economics, 1980