Hedging with Linear Regressions and Neural Networks
Risk Management
2021-06-15 v3 Machine Learning
Mathematical Finance
Statistical Finance
Machine Learning
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. However, a similar benefit arises by simple linear regressions that incorporate the leverage effect.
Keywords
Cite
@article{arxiv.2004.08891,
title = {Hedging with Linear Regressions and Neural Networks},
author = {Johannes Ruf and Weiguan Wang},
journal= {arXiv preprint arXiv:2004.08891},
year = {2021}
}
Comments
Forthcoming in the Journal of Business & Economic Statistics