Option pricing with modular neural networks(Article)(Open Access)
- aFaculty of Business Administration, Lakehead University, Thunder Bay, ON P7B 5E1, Canada
- bDepartment of Economics, Simon Fraser University, Burnaby, BC V5A 1S6, Canada
- cFaculty of Engineering, University of Novi Sad, 21000 Novi Sad, Serbia
Abstract
This paper investigates a nonparametric modular neural network (MNN) model to price the S&P-500 European call options. The modules are based on time to maturity and moneyness of the options. The option price function of interest is homogeneous of degree one with respect to the underlying index price and the strike price. When compared to an array of parametric and nonparametric models, the MNN method consistently exerts superior out-of-sample pricing performance. We conclude that modularity improves the generalization properties of standard feedforward neural network option pricing models (with and without the homogeneity hint). © 2009 IEEE.
Indexed keywords
| Engineering uncontrolled terms | Generalization propertiesModular neural networksNon-parametricNon-parametric modelsNonparametric methodsOn timeOption pricesOption pricingOption pricing models |
|---|---|
| Engineering controlled terms: | CostsFeedforward neural networks |
| Engineering main heading: | Commerce |
- ISSN: 10459227
- CODEN: ITNNE
- Source Type: Journal
- Original language: English
- DOI: 10.1109/TNN.2008.2011130
- Document Type: Article
Gradojevic, N.; Faculty of Business Administration, Lakehead University, Canada;
© Copyright 2009 Elsevier B.V., All rights reserved.
Cited by 55 documents
(2024) Computational Economics
(2024) Annals of Operations Research
(2024) ACM International Conference Proceeding Series