Option valuation under no-arbitrage constraints with neural networks

Cao, Yi and Liu, Xiaoquan and Zhai, Jia (2021) Option valuation under no-arbitrage constraints with neural networks. European Journal of Operational Research, 293 (1). pp. 361-374. ISSN 03772217

PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
Available under Licence Creative Commons Attribution.
Download (3MB) | Preview


In this paper, we start from the no-arbitrage constraints in option pricing and develop a novel hybrid gated neural network (hGNN) based option valuation model. We adopt a multiplicative structure of hidden layers to ensure model differentiability. We also select the slope and weights of input layers to satisfy the no-arbitrage constraints. Meanwhile, a separate neural network is constructed for predicting option-implied volatilities. Using S&P 500 options, our empirical analyses show that the hGNN model substantially outperforms well-established alternative mod els in the out-of-sample forecasting and hedging exercises. The superior prediction performance stems from our model’s ability in describing options on the boundary, and in offering analytical expressions for option Greeks which generate better hedging results.

Item Type: Article
Keywords: Finance;Artificial neural networks; Implied volatilities; Option greeks; Hedging
Schools/Departments: University of Nottingham Ningbo China > Faculty of Business > Nottingham University Business School China
Identification Number: https://doi.org/10.1016/j.ejor.2020.12.003
Depositing User: QIU, Lulu
Date Deposited: 04 Jun 2021 01:12
Last Modified: 04 Jun 2021 01:12
URI: http://eprints.nottingham.ac.uk/id/eprint/65405

Actions (Archive Staff Only)

Edit View Edit View