Option pricing with genetic algorithms: a second report

Abstract

The cross-fertilization between artificial intelligence and computational finance has resulted in some of the most active research areas in financial engineering. One direction is the application of machine learning techniques to pricing financial products, which is certainly one of the most complex issues in finance. In the literature, when the interest rate, the mean rate of return and the volatility of the underlying asset follow general stochastic processes, the analytical solution is usually not available. Over the last two years, artificial neural nets have been applied to solve option pricing numerically. However, so far, there is no applications based on evolutionary computation in this area. In this paper, we illustrate how genetic algorithms (GAs), as an alternative to neural nets, can be potentially helpful in dealing with option pricing. In particular, we test the performance of basic genetic algorithms by applying them to the determination, of prices of European call options, whose exact solution is known from Black-Scholes option pricing theory. The solutions found by basic genetic algorithms are compared with the exact solution, and the performance of GAs is evaluated accordingly