A Hybrid Option Pricing Model Using a Neural Network for Forecasting Volatility

Abstract

A great deal of research in the financial domain involves the development of models for pricing financial derivatives, such as options. The Black-Scholes model is the standard approach used for pricing financial options. However, although being theoretically strong, option prices valued by the model often differ from the prices observed in the financial input data for improving the estimation of option market prices. The resulting option price is then a summation between the Black-Scholes model result and the actual market option prices. The Hybrid system with a neural network for estimating volatility provides better performance than either the Black-Scholes model with historical volatility, or the Black-Scholes model with volatility valued by the network.

Department(s)

Engineering Management and Systems Engineering

Keywords and Phrases

Backpropagation; Benchmarking; Brownian Movement; Data Reduction; Digital Signal Processing; Finance; General Regression Neural Network (GRNN); Genetic Algorithms; Mean Absolute Deviation (MAD); Mean Squared Error (MSE); Neural Networks; Option Pricing

Document Type

Article - Conference proceedings

Document Version

Citation

File Type

text

Language(s)

English

Rights

© 2003 American Society of Mechanical Engineers (ASME), All rights reserved.

Publication Date

01 Jan 2003

This document is currently not available here.

Share

 
COinS