Monte Carlo methods have long been used in computational finance to solve problems where analytical solutions are not feasible or are difficult to formulate. However, these methods are computationally intensive making it challenging to implement and adopt. In the last decade, advances in hardware, increasing processor speeds and decreasing costs have made it easier to adopt Monte Carlo methods to solve numerically intensive problems. With growing access to data and demand for quicker results, researchers are constantly looking for better ways to implement algorithms using Monte Carlo methods.
In this article, we share some of our observations and demonstrate various ways MATLAB could be used to implement Monte Carlo methods. We take a case study of pricing Asian options and show various approaches to implementing them in MATLAB.
Note: This article was co-authored by Sri Krishnamurthy when he was employed at MathWorks.
Additional resources on Black Litterman model can be found here: