Title :
Do-ahead replaces run-time: a neural network forecasts options volatility
Author :
Malliaris, Mary ; Salchenberger, Linda
Author_Institution :
Dept. of Manage. Sci., Loyola Univ., Chicago, IL, USA
Abstract :
Compares three methods of estimating the volatility of daily S&P 100 Index stock market 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
Keywords :
finance; neural nets; stock markets; Black-Scholes model; do-ahead method; historical volatility; implied volatility prediction; neural network; options pricing; run-time method; stock market options volatility; stock market traders; Calendars; Economic forecasting; Forward contracts; History; Input variables; Motion measurement; Neural networks; Predictive models; Pricing; Runtime;
Conference_Titel :
Artificial Intelligence for Applications, 1994., Proceedings of the Tenth Conference on
Conference_Location :
San Antonia, TX
Print_ISBN :
0-8186-5550-X
DOI :
10.1109/CAIA.1994.323630
