10-40% more accurate than perpetual inventory
AI models engineered for uncertainty build a more accurate picture of reality
Most inventory systems rely on constant upkeep to stay accurate. This process is labor-intensive and can’t keep up when faced with the spoilage, mis-scans, and random weight items of fresh departments. Perpetual inventory drifts fast, store teams are always recounting, and orders are always off.
Afresh took a different approach and developed machine learning models that actually account for uncertainty and perishability from the start to build a more reliable decision-making foundation.
Every order, production plan, and DC buy starts with a position on what's actually on the shelf, in the backroom, and in transit. When that inventory position is wrong, grocers lose margin in several ways: high shrink or holding costs on overstocked items, stockouts on items the system thought were available, and wasted labor on constant inventory checks and counts.
Traditional Inventory Logic Doesn’t Work in Grocery
Perpetual Inventory (PI) is based on a simple mathematical approach designed for retail categories where data inputs stay clean and predictable. But PI breaks when it gets to fresh:
Afresh started in fresh because it was the highest-impact area for grocers—and the most underserved by technology. Since it didn’t exist, we designed models to handle spoilage, random weight, in-store transformation, and inconsistent counts—and still determine accurate inventory positions.
Three things have to be true for a system to make accurate decisions in grocery: the inputs have to be usable, they have to be modeled probabilistically to account for uncertainty, and the calculation of uncertainty has to match the real world. Afresh built models for all three.
Afresh scores every data input for quality, cleans inaccurate or mis-matched values, and redacts bad inputs so estimates downstream reflect real store conditions.
Learn more about data management →
Unlike other systems, Afresh doesn’t expect or need the system of record to be 100% correct, because it never is—especially once you get to fresh departments.
Instead of arriving at an inventory estimate with an arithmetic approach (inventory = shipments received - items sold), our AI models every input probabilistically. It considers things like the quality of the sales and shipments data, factoring in likelihood of mis-scans, and the demand and perishability models to create a probability curve of what true inventory positions might be. A probability curve covers every possible outcome and its likelihood. So instead of determining "inventory = 10 cases," Afresh calculates "85% chance inventory = 10 cases or fewer."
Afresh models inventory this way for every item, creating better inputs that lead to more accurate order recommendations across stores and distribution centers, as well as more reliable inventory positions for e-commerce feeds.
Learn more about demand forecasting →
These store- and item-level probability curves for demand, inventory, and perishability feed into Afresh’s decision making engine. This engine then simulates orders across in-stocks, shrink, display sizes, and freshness, analyzing thousands of possible orders to find the single best one that maximizes profits.
See how Afresh coordinates decisions across the supply chain →
Store Orders: Afresh’s inventory model provides an estimate for each item, so order recommendations reflect what's actually sellable on the floor and what a store will need.
Inventory Management: Items with high inventory uncertainty trigger a count request, so the item shows up on the to-do list when an associate starts inventory counts in Afresh.
Production Planning: Inventory positions feed into prep and bake schedules so teams plan against what's actually available and likely to sell.
Period Ending Inventory: Afresh’s understanding of inventory position updates daily, so at period close, Afresh can pre-populate estimates for every item. Teams review and adjust the items that need attention instead of starting every count from zero.
DC Buying: At the DC level, the same probabilistic model keeps inventory positions calibrated across the supply chain. Buyers size weekly purchase orders and evaluate opportunity buys against what stores can actually move and what the DC can actually fulfill.
Discover why Afresh is the cornerstone solution for leading retailers.