Do-Ahead Replaces Run-Time: A Neural Network Forecasts Options Volatility

Authors

Mary Malliaris, Loyola University Chicago
Linda Salchenberger, Marquette UniversityFollow

Document Type

Conference Proceeding

Language

eng

Publication Date

3-1-1994

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Source Publication

Proceedings of the Tenth Conference on Artificial Intelligence for Applications, 1994

Source ISSN

9780818655524

Abstract

In this paper, we compare three methods of estimating the volatility of daily SBP 100 Index for options. The implied volatility, calculated via the Black-Scholes model, is currently the most popular method of estimating volatility and is used by traders in the pricing of options. Historical volatility has been used to predict the implied volatility, but the estimates are poor predictors. A neural network for predicting volatility is shown to be far superior to the historical method.

Comments

Published as part of the Proceedings of the Tenth Conference on Artificial Intelligence for Applications, 1994, San Antonia, TX. DOI.

Linda Salchenberger was affiliated with Loyola University Chicago at the time of publication.

Recommended Citation

Malliaris, Mary and Salchenberger, Linda, "Do-Ahead Replaces Run-Time: A Neural Network Forecasts Options Volatility" (1994). Management Faculty Research and Publications. 286.
https://epublications.marquette.edu/mgmt_fac/286