Option valuation under no-arbitrage constraints with neural networks
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 layer...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
2021
|
| Subjects: | |
| Online Access: | https://eprints.nottingham.ac.uk/65405/ |
| _version_ | 1848800223254544384 |
|---|---|
| author | Cao, Yi Liu, Xiaoquan Zhai, Jia |
| author_facet | Cao, Yi Liu, Xiaoquan Zhai, Jia |
| author_sort | Cao, Yi |
| building | Nottingham Research Data Repository |
| collection | Online Access |
| description | 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. |
| first_indexed | 2025-11-14T20:48:09Z |
| format | Article |
| id | nottingham-65405 |
| institution | University of Nottingham Malaysia Campus |
| institution_category | Local University |
| language | English |
| last_indexed | 2025-11-14T20:48:09Z |
| publishDate | 2021 |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | nottingham-654052021-06-04T01:12:24Z https://eprints.nottingham.ac.uk/65405/ Option valuation under no-arbitrage constraints with neural networks Cao, Yi Liu, Xiaoquan Zhai, Jia 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. 2021-08-16 Article PeerReviewed application/pdf en cc_by https://eprints.nottingham.ac.uk/65405/1/Combine.pdf Cao, Yi, 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 Finance；Artificial neural networks; Implied volatilities; Option greeks; Hedging http://dx.doi.org/10.1016/j.ejor.2020.12.003 doi: 10.1016/j.ejor.2020.12.003 doi: 10.1016/j.ejor.2020.12.003 |
| spellingShingle | Finance；Artificial neural networks; Implied volatilities; Option greeks; Hedging Cao, Yi Liu, Xiaoquan Zhai, Jia Option valuation under no-arbitrage constraints with neural networks |
| title | Option valuation under no-arbitrage constraints with neural networks |
| title_full | Option valuation under no-arbitrage constraints with neural networks |
| title_fullStr | Option valuation under no-arbitrage constraints with neural networks |
| title_full_unstemmed | Option valuation under no-arbitrage constraints with neural networks |
| title_short | Option valuation under no-arbitrage constraints with neural networks |
| title_sort | option valuation under no-arbitrage constraints with neural networks |
| topic | Finance；Artificial neural networks; Implied volatilities; Option greeks; Hedging |
| url | https://eprints.nottingham.ac.uk/65405/ https://eprints.nottingham.ac.uk/65405/ https://eprints.nottingham.ac.uk/65405/ |