In this research, forecasting of the option prices of Nikkei 225 index futu
res is carried out using backpropagation neural networks. Different results
in terms of accuracy are achieved by grouping the data differently. The re
sults suggest that for volatile markets a neural network option pricing mod
el outperforms the traditional Black-Scholes model. However, the Black-Scho
les model is still good for pricing at-the-money options. In using the neur
al network model, data partition according to moneyness should be applied.
Those who prefer less risk and less returns may use the traditional Black-S
choles model results while those who prefer high risk and high return may c
hoose to use the neural network model results. (C) 2000 Elsevier Science Lt
d. All rights reserved.