A stock-out early warning tool for a consumer goods brand. It predicts which products will run out in which stores before the shelf goes empty, then tells planners whether to reorder, transfer stock from a nearby store, or expedite the delivery.
The brand saw stock-outs only after they happened, in last week's sales report. By then the shopper had already bought a competitor's product. RestockIQ looks ahead instead of back.
For each product in each store: current stock ÷ daily sales, adjusted for upcoming promotions, compared with the next delivery date.
Every gap is ranked by how much revenue it would lose, so planners fix the most expensive problems first.
Transfer from a nearby store if one has spare stock, otherwise expedite or reorder. Overstock gets flagged too.
on-shelf availability, below the 95% retailers expect
of revenue lost to empty shelves each season
of warning: stock-outs were found in reports after the fact
Baseline from a one-season audit across 3 retail partners (sample data).
"I have 400 product–store combinations. Which 10 do I fix today?"
Job to be done: prevent stock-outs with the least cost and effort.
"The retailer calls me before I even know we're out."
Job to be done: protect the relationship and the shelf space with the retailer.
"Show me availability and what it's costing us."
Job to be done: hit the retailer's availability target without overstocking.
Discovery: 9 stakeholder interviews, 2 store visits, review of retailer scorecards (sample).
Pick a product, change stock, sales rate or delivery timing, and turn on a promotion to see when the shelf goes empty and what RestockIQ recommends.
If planners get a ranked stock-out warning 5+ days ahead, at least half of stock-outs can be prevented without adding inventory.
Piloted with one retail partner's 40 stores for a season, compared with matched stores still on weekly reports.
Runs on the retailer's daily sales and stock feed with simple, visible math. No AI model was needed to prove the value.
| Product | Store | Cover | Delivery in | Sales at risk | Status | Recommended fix |
|---|
All data is illustrative sample data, created for this portfolio.
The first idea was simply to order more stock everywhere. I pushed for transfers from nearby stores first, because more inventory hides the problem and ties up cash. In the pilot, 38% of stock-outs were fixed by transfers alone, with no extra inventory.
The key product trade-offPDFs open in a new tab; Excel and PowerPoint files download. Portfolio case study; all data is illustrative sample data.
Beauty & Cosmetics