Using the Graphics Processing Unit to Evaluate American-Style Derivatives

Abstract

In this article, the authors apply graphics processing unit (GPU) computation to an American option pricing problem via Monte Carlo (MC) simulations and particle swarm optimization (PSO). Given that computations in both MC and PSO can be vectorized and made independent, the valuation can be readily performed on GPUs. As a result, we can increase the accuracy of the valuation by increasing MC paths and particles without spending more time. For example, with a large number of particles (but allocated to GPUs), convergence can be reached in very few steps. The method introduced in this article can be extended to a wide variety of exotic derivatives or a large portfolio of diverse derivatives (known as an eigen portfolio). This is helpful in both trading and risk management.