RSI began with a patented, cloud-based predictive analytics engine for inventory optimization. Everything built since extends that same science outward, layer by layer, as clients asked for more.
RSI began with simulation-based Inventory Optimization and has expanded into a broader set of supply-chain decision capabilities. A deep analytics layer now spans those capabilities, using advanced and increasingly agentic tools to uncover patterns, interpret results, and accelerate decision support. Surrounding the technology is RSI practitioner expertise, the human layer that connects analytics to real operating decisions.
Where RSI started and still the foundation: a patented, simulation-based engine that models real demand and lead-time variability at the item × location level.
Network Balancing, Prioritized Planning (PRIO), and AI Automation leverage our core IO capability. Each extends the core into a decision domain clients asked RSI to help with.
Advanced and increasingly agentic analysis that works across every capability, reading what goes into the engine and what comes out of it to surface patterns and answer questions faster.
Practitioners who have run planning, inventory, and distribution organizations. They are the primary interface to clients, interpreting the analytics and turning them into operating decisions. Our experts provide ongoing Strategic Operation Services to help ensure great supply chain decisions are repeatable.
Traditional inventory optimization formulas and algorithms create inventory deficiencies or surpluses because they cannot account for the required supply chain variables to accurately determine inventory levels. By not accounting for these critical supply chain variables, these methods essentially do not represent each inventory item’s actual unique variation and constraints.
Our optimization software simulates real-world client environments, predicts optimum inventory levels at an item/location level, and enables our clients to realize better business outcomes by eliminating inventory imbalances and quantifying risk.
which ties up working capital, consumes valuable warehouse space, and drives costly relocation
which often results in poor on-time delivery and lost sales/clients along with costly expedites
Predictive analytics is a powerful technology that can improve an enterprise’s efficiency and profitability. However, despite the obvious benefits, introducing predictive analytics does come with some challenges. One such challenge is the notion that predictive analytics technology represents a “black box” that is difficult to understand and explain.
RSI’s patented technology is not based on static formulas or algorithms. We use a Monte Carlo simulation technique to simulate supply chains for any given item in any given location.
During the simulation process, daily inventory goes up due to anticipated receipts of supply and goes down due to anticipated demand or any other valid consumption of inventory. During the simulation, RSI pays particular attention to two things:
the average on-hand inventory quantity throughout the simulation
is this simulated inventory quantity sufficient to meet demand requirements at the desired customer service level?
As inventory levels increase or decrease during a simulation, a lot of factors come into play. RSI works with our clients to collect all relevant input parameters that enable our simulations to best reflect real-world behavior of their items in their business environment. It is crucial that these input parameters reflect real-world processes and values in order to properly simulate how inventory is expected to change over time.
RSI harnesses the power of AWS cloud computing to simulate real-word conditions in minutes. Our patented technology leverages a probabilistic Monte Carlo model that accurately and correctly represents all real-world factors (there are about 10) affecting actual inventory and service-level behavior. RSI also utilizes statistics that correctly represent demand and supply variability. The model generates a minimum of 2000 independent inventory behavior simulations for your entire supply chain at the individual item level. This quantifies and accounts for any randomness, intermittency, uncertainty and variance in the determination of optimal inventory levels.
We have found that processing a minimum of 2,000 Monte-Carlo-style iterative simulations best drives a high-confidence statistical probability that the RSI target inventory level will meet the required service level for each item at each location.
Start with a Supply Chain Assessment. You scope what gets evaluated.
