Due to some unrealistic assumptions, the traditional Black-Schloes formula systematically misprices options. This paper applies an alternative multilayer feed-forward neural network to price S&P 500 index calls. Both the in-and out-of-smaple accuracy are far better for the ANN than for the Black-Chloes formula. On addition, ananysis of the estimated weigths reveals that the economic implications of the ANN are consistent with call price properties, and for the first time open interest is concluded that ANN is a good alternative to the traditional Black-Scholes formula when its underlying assumptions are violated.
展开▼