### Monte Carlo Tool Best Uses Author: Andrew Baker
A Monte Carlo tool could be a fantastic add-on to your business decision-making effectiveness. Here are a few case studies to help you determine if it'll be a good match for your business.
Monte Carlo simulation was named after the popular gambling city in Europe because its strength comes from generating and showing multiple possible outcomes, given a wide range of variable inputs, and their statistically driven probabilities. Since this appeared to be the perfect casino predictor, the method was given the Monte Carlo moniker.
All industries are subject to variances and predictive error. Even if you're in the most stable area of the economy, there is definitely a variety of variables than can increase or decrease the probabilities of any potential business outcome. This is how a Monte Carlo tool can be powerful.
For instance, let us presume you own a string of beauty parlors and you have 15 years of monthly past financial data to work with. Many months produce positive cash flows and others produce falling cash flows. You have an interest in computing the probability of positive cash flows in any subsequent quarter because you are determining the amount of cash to borrow to build another location. If you take the past 15 years of monthly cash flows and input them into the Monte Carlo tool, then run 5,000 simulations, you should get an excellent probability distribution of cash flows with which to work. This tool will provide projected statistical odds of above-zero cash flows, of a specified value, with a certain confidence level. At the end you will get an answer like "There is probably a 75% probability that the cash flows will be greater than $12,000, five percent probability the cash flows will be less than -$5,000 and 7.2% possibility the cash flows will be greater than $35,000 in the following month."
One other illustration is the probability of a break down lasting greater than 1 day in a fleet of delivery vans. Using historical failure data, you may use a Monte Carlo tool to replicate the likelihood of 1, 2, 4 and 7-day mechanical breakdowns in your truck fleet. Of course, this assumes the fleet consists of similar trucks with the same average age and condition, driving on similar roads as the past data shows. You then use these odds, multiplied times the average expense of repair and decrease in shipping fees, to estimate future breakdown costs to the company. In a highly competitive business such as transportation, predicting your costs with a fine accuracy standard is crucial to pricing the service or product and making sure you don't lose money.
A far more advanced way to use Monte Carlo tools would be to initially develop an explanatory model for supply and demand in Excel or computer code, using economic and demographic inputs such as unemployment, rates of interest, age group, sex, and so on. Then, the Monte Carlo simulation is processed thousands of times on many levels of inputs, with every variable potentially restricted by high and low limits. The simulation then outputs a distribution of estimated supply and demand figures for a variety of inputs it was arbitrarily provided. From this probability distribution or histogram, you can then derive the potential range of supply and demand, variations as to each input, and identify percentage odds at any level.
These are merely a few of the great variety of uses of a Monte Carlo tool for industry analyses. |