Cookies?
Library Header Image
LSE Research Online LSE Library Services

Hedging with linear regressions and neural networks

Ruf, Johannes ORCID: 0000-0003-3616-2194 and Wang, Weiguan (2022) Hedging with linear regressions and neural networks. Journal of Business and Economic Statistics, 40 (4). 1442 - 1454. ISSN 0735-0015

[img] Text (Hedging With Linear Regressions and Neural Networks) - Published Version
Available under License Creative Commons Attribution Non-commercial No Derivatives.

Download (2MB)

Identification Number: 10.1080/07350015.2021.1931241

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 minimize 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.

Item Type: Article
Official URL: https://www.tandfonline.com/toc/ubes20/current
Additional Information: © 2021 The Authors
Divisions: Mathematics
Subjects: H Social Sciences > HB Economic Theory
H Social Sciences > HA Statistics
Date Deposited: 09 Dec 2020 11:15
Last Modified: 30 Nov 2024 02:06
URI: http://eprints.lse.ac.uk/id/eprint/107811

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year

View more statistics