Retail · USA · Inventory
Demand forecasting & ABC inventory analysis
A US home-goods retailer lost sales to empty shelves on bestsellers while overpaying to store slow movers. The brief: forecast demand across 18,400 SKUs and rebuild the buying plan around it.
Forecast accuracy
92.4%
MAPE 7.6%
Bestseller stockouts
−63%
fewer lost sales
Holding cost
−28%
$3.1M freed up
Inventory turnover
+19%
year over year
Actual sales vs model forecast
monthly, thousand units · dashed = 3-month forecast
ABC assortment analysis
share of SKUs vs share of revenue
◆ Findings
- Class A (7% of SKUs) drove 71% of revenue — and ran out most often.
- Bestseller demand had clear weekly and seasonal cycles that manual buying ignored.
- 34% of class-C items hadn't sold in 90 days and were freezing working capital.
✓ What we did
- Switched class A to forecast-driven auto-replenishment with a 14-day safety stock.
- Retired 1,240 dead SKUs and reinvested the budget into proven sellers.
- Added out-of-stock alerts seven days before a bestseller hits zero.
Have a project like this?
Tell us what you are building. We reply within one business day with a clear plan and a fixed quote.
Start your project