Option Pricing With Modular Neural Networks

25 Pages Posted: 27 Jan 2007  

Nikola Gradojevic

University of Guelph, Department of Economics and Finance; University of Bologna - Rimini Center for Economic Analysis (RCEA)

Ramazan Gencay

Simon Fraser University

Date Written: 2007

Abstract

This paper applies a non-parametric 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 homogenous of degree one with respect to the underlying index price and the strike price. We find that modularity improves the generalization properties of standard feedforward neural network option pricing models (with and without the homogeneity hint), relative to the Black-Scholes model.

Keywords: Option Pricing, Modular Neural Networks, Non-parametric Methods.

JEL Classification: C45, G12

Suggested Citation

Gradojevic, Nikola and Gencay, Ramazan, Option Pricing With Modular Neural Networks (2007). Available at SSRN: https://ssrn.com/abstract=959544 or http://dx.doi.org/10.2139/ssrn.959544

Nikola Gradojevic (Contact Author)

University of Guelph, Department of Economics and Finance ( email )

50 Stone Road East
Guelph, Ontario N1G 2W1
Canada

HOME PAGE: http://https://www.uoguelph.ca/economics/users/nikola-gradojevic

University of Bologna - Rimini Center for Economic Analysis (RCEA) ( email )

Via Patara, 3
Rimini (RN), RN 47900
Italy

Ramazan Gencay

Simon Fraser University ( email )

Department of Economics
8888 University Drive
Burnaby, British Columbia V5A 1S6
Canada

Paper statistics

Downloads
283
Rank
86,719
Abstract Views
1,368