Study on option pricing by applying hybrid wavelet networks and genetic algorithm
Cailou Jiang · Journal of systems engineering · 2010
The implied volatility rates of varied kinds of options are different because of volatility smile effects.How to determine the optimal weights of the implied volatility rates of varied kinds of options is an important issue in option pricing.A hybrid wavelet neural network based on the Black-Scholes model is proposed in this paper,and some hybrid forecasting models combining the hybrid wavelet neural network and genetic algorithm are built.In such an approach options are classified according to their moneyness,and the weighted implied volatility rates are regarded as the input of the neural network.A genetic algorithm is used to determine the optimal weights of the implied volatility rates of different kinds of options.Case study on Hong Kong derivative market shows that these hybrid models are better than the conventional Black-Scholes model and the other neural network models.