Modern business planning technology goes beyond modeling what-if scenarios. The right mathematical methods combined with software built for ease-of-use provide proper risk-quantifications and enable supply chain decision-making aligned with (and in the language of) corporate goals. Most tools can run what-if models, but they are still deterministic in nature and limited in value.
Going into 2020, make sure your business planning software uses Monte Carlo Simulation and can quantify (dollarize) risks to optimize business plans.
A Practical Guide to Supply Chain Planning Maturity
Monte Carlo Simulation
“Monte Carlo simulations are used to model the probability of different outcomes in a process that cannot easily be predicted due to the intervention of random variables. It is a technique used to understand the impact of risk and uncertainty in prediction and forecasting models.” – Investopedia.com.
Let’s begin with a very simple example of how Monte Carlo Simulation (MCS) would work in the real world. In this example, the objective guesses the total value of combined numbers on a dice roll. The winning number in the image below would be 12.
The smartest bet or “guess” in this game is to choose the most probable value, regardless of gut feel, or results of the game immediately preceding. To understand the most probable winning value, you’d have to roll the dice many times and count all of the winning values to see which occurred the most. The more times rolled (we’re talking like 50,000 here) the more accurate your calculations.
Rather than rolling the dice thousands of times, you can apply MCS, which simulates the rolling of the dice (and the thousands of iterations) instantaneously and tells you the probability of each value occurring. If we do this we will now know, mathematically, that the value 7 is the most probable, about 17% likely to occur, with the values 8 and 6 trailing at about 14% likelihood.
Yes, we could have drawn some basic conclusions that would lead us to bet on 7 even without MCS. Mainly, that the winning value of 7 has a variety of ways (combinations of die values) to be reached (like 6 and 1, 5 and 2, 4 and 3, and all of the inverse) as opposed to the value 2 which only occurs with a single pair of 1s.
Although we can reasonably conclude that 7 is the right bet in this game without advanced analytic techniques, there are other real-world examples with more complex and uncertain variables. For example, calculating optimal safety stock levels based on historical sales data and current inventory levels, knowing that lead times and demand are somewhat uncertain, and adhering to a strict 95% service level is a scenario best played out with MCS.
Monte Carlo Simulation assists in Supply Chain Management decisions by incorporating uncertain variables into iterative simulations, allowing decision-makers to “play out” what the future demand (or lead times) might look like. Leaders can make decisions with simulated data at their fingertips, rather than formulating simple best, average, and worst-case scenarios that do not truly account for the probability of risks.
“The popularity of Monte Carlo Simulation is due to its versatility and ease of use. The MCS method is a quantitative method that involves assigning individual types of risk to the probability of its occurrence. The consequence of an unexpected occurrence may be an unplanned change in the cost and completion date of the order or contract that can be treated as a project.” – Supply Chain Risk Management by Monte Carlo Method.
Impact of Advanced Analytics Forecasting