American option pricing using multi-layer perceptron and support vector machine

Abstract

An option is the right to buy or sell an underlying asset at a future date. The field of option pricing produces a challenge because of the complexity with pricing American styled options which cannot be done by the Black-Scholes equations for option pricing. A multi-layer perceptron neural network has been used before to price these options with limited success. In this paper we will compare the performance of a multi-layer perceptron neural network and a support vector machine in pricing American styled options. It was found that a support vector machine approach provided much better results than that found with multi-layer perceptrons.