Monte Carlo Simulation – Learning Roadmap

2 mins read time

Pricing a financial instrument is not an exact science. There may be formulae, mathematics, derivation, proofs and exact models but in essence pricing financial securities in real-world markets is more along the lines of a science of approximation.

One approach to pricing these instruments is to use a Monte Carlo Simulator. A simulation is an experiment, and an MC simulator may be considered a machine that can churn out a series of experiments. The simulator will behave in a certain fashion (i.e. produce symmetric, asymmetric, normal and skewed, with thin tails or long fat tails) depending on the tool used to build the machine (i.e. the choice of distribution). By definition, it will always be inaccurate and an approximation to the real world.

Monte Carlo Simulation – Learning Roadmap - All models are wrong

What are the prerequisites?

A useful introduction to some of the concepts mentioned in this roadmap are the following online courses:

What topics are covered?

How can I build Monte Carlo Simulators in EXCEL?

The Monte Carlo (MC) simulation concept is best explained through example and in the following courses, we explain basic MC principles by building simulators in EXCEL for currencies, commodities and equities. We also explain the link between increasing the number of trials and increasing the accuracy of simulation results:

The following post suggests a solution for addressing the normality assumption challenge by replacing the normal distribution with the historical distribution.

What are some applications of Monte Carlo Simulations that I will learn?

In the next stage we consider Monte Carlo simulation applications:

Monte Carlo Simulation - Learning Roadmap - Exotic Option pricing using Monte Carlo Simulation
Exotic Option pricing using Monte Carlo Simulation

What are the additional topics I can read up on?

Case Studies

Premium Content