As decision makers, we are constantly faced with uncertainty, ambiguity, and variability. The cloud shift is a perfect example where businesses are just beginning to learn how to navigate unknown cloud usage pricing models and costs. How much will cloud cost to operate annually? It is often not easy to estimate since there are many unknown variables. Monte Carlo Simulation is an analytics technique that could be explored to better understand the range of possible outcomes.
Monte Carlo Simulation
Monte Carlo Simulation arms decision makers with objective probabilities for all possible outcomes empowering informed decision making in uncertain conditions. Historically it has been used in stock market analysis, financial services, software development, military, healthcare, utilities, transportation, pricing and research. Simulation helps in situations where many decision model factors have inherent uncertainty such as supplier costs, unknown market demand and competitor pricing.
Monte Carlo Simulation evaluates numerous scenarios for planning, decision making and risk mitigation. Result accuracy and insights gained from using this specific analytic technique far surpass limited what-if scenario analysis.
Applied Statistical Probability
Monte Carlo Simulation is a stochastic analysis technique that applies value ranges for non-deterministic or unknown variables with probability theory to create thousands of “what-if” scenarios. Computer automated simulation models substitute the analyst provided range of random variable values according to expected variables statistical probability distributions. It is the variable probability distributions and evaluation across all possible combinations of these variables that allow for realistic evaluation of scenario uncertainty.
This analytic technique is not perfect. It is still subject to human analyst consideration of worst and best case variable values. Although historical data is often used as a baseline, extreme situations may not be present in the data or even imagined by the analyst designing the model.
An example of unfathomable extreme conditions is the October 2008 stock market crash.
Personally, I will never forget 2008. That experience shaped several of my financial survival anxieties even though I was lucky. During that recession I helped executives keep the lights on per se reinventing business models in never considered, worst-case conditions. My data and predictive modeling skills were invaluable for them… and even for my own family since my husband’s employer went bankrupt. It was scary.
Today I still live modestly as thousands of my peers get replaced by foreign and H1B workers every month in the USA. I ease my fears by exploring risk models, spending wisely, saving for a rainy day and driving my own destiny.
I digressed… Let’s get back to simulation and addressing uncertain risks.
According to Douglas Hubbard, author of How to Measure Anything: Finding the Value of Intangibles in Business, the frequency of rare catastrophic events is much higher than most models assume. “If I fill a bucket with dice and roll them, this activity will yield what we know as a normal distribution. But most of the risks we worry about modeling for in the financial world do not behave this way. Financial markets behave more like earthquakes, forest fires, and tsunamis. Their interrelated components mean that the whole system can be stressed. The failure of one component causes the failure of many other things. The single biggest risk for any organization—or nation—is the lack of validating risk analysis methods. Precautions or analysis of financial volatility are useless if inadequately assessing risk to begin with.”
One of the most actionable aspects of Monte Carlo Simulations is getting deeper insight into the specific uncertain variables that have the most influence via Sensitivity Analysis. Sensitivity Analysis provides a ranked shortlist of variables that have significant impact on various outcomes. The knowledge gained from Sensitivity Analysis aids decision makers in knowing key influencing variables to manage versus waste time and money on minimally relevant areas.
As organizations get more sophisticated with analytics, I expect to see simulation used more often. If you want to explore Monte Carlo Simulations, a few tried-and-true software packages include @RISK, Oracle Crystal Ball, and Frontline Systems Analytic Solver Platform. You could also build your own solution with open source R or Python. If you know of other solutions, please share them with me.
I’d love to see someone apply simulation to cloud pricing models versus the static estimator tools and growing sea of third-party cloud estimator apps. The fact that there is a niche market of cloud estimator apps indicates there is way too much cloud cost complexity for decision makers to grasp. If I get a chance over the next few months, I might try applying simulation models to Amazon, Azure and Google Cloud estimates.
By using a prescriptive analytics process and techniques like Monte Carlo Simulation, you not only get insight into what could happen in the future but also invaluable insight into what actions can be taken that truly do make a difference and mitigate risks. If you analyze data for a living, Monte Carlo Simulation should be in your repertoire of analytical skills.