How We Do It – Supply Chain Predictive Analytics Software
Sure, we have a technical White Paper that will break things down — but what about a simple explanation?
Put simply, RSI takes the guesswork out of determining the minimal amount of inventory required for a business to achieve defined service levels; thus, eliminating inventory imbalances and enabling businesses to quantify risk. We do this utilizing real-world simulations of a company’s supply chain environment. We simulate the supply chain for any given item in any given location. We run the simulation for a defined period, let’s say for 90 days, but it can be any length of time. During the simulation, daily inventory goes up due to receipts and goes down due to demand or any other valid consumption. We then iterate the simulation using Monte Carlo methodology to find the optimal answer to this question: What’s the minimum inventory level that has the highest probability of meeting the required service level?
Monte Carlo simulations build models of possible results by substituting a range of values, in other words a probability distribution, for any supply chain factor that has inherent uncertainty. It then calculates results over and over, each time using a different set of random values from the probability functions. Depending upon the number of uncertainties and the ranges specified for them, a Monte Carlo simulation could involve thousands or tens of thousands of recalculations before it is complete. Monte Carlo simulation produces distributions of possible correct outcome values.
Simulation means we start with a beginning on-hand inventory quantity and simulate daily changes in inventory levels over a set period of time. This period is configurable within RSI, but for sake of this discussion let’s go with a quarter (90 calendar days). During the simulation, daily inventory goes up due to receipts of supply and goes down due to demand or any other valid consumption of inventory. While we’re simulating this inventory behavior, we pay close attention to two things: 1) what is the average on-hand inventory quantity; 2) is inventory quantity sufficient to meet demand requirements given a defined service level. We then iterate the simulation using Monte Carlo methodology to find the optimal answer to this question: What is the minimum inventory level that has the highest probability of meeting our required service level? (Incidentally, we run a minimum of 2,000 Monte-Carlo-style iterative simulations. We have found that this volume best drives a high-confidence statistical probability that the RSI target inventory level really will meet the required service level.)
At RSI, we believe our Better Science is worthy of trust. So, we decided the right approach is to explain to people exactly how we do what we do. We aim to avoid the “black box” approach where companies say, “just trust us”. Our analyses perform no “behind the curtain” wizardry, and we will take as long as required with as much detail needed for you to fully comprehend exactly how we reached the results. Once you understand it, we’re sure you’ll agree our patented predictive analytics are far superior to any algorithm or formula.inventory techmonte carlomonte carlo simulationsoftware techsupply chainSupply Chain Softwaresupply chain solutiontechnology