CASE STUDY

Sporting Goods Retailer: ML-Driven Inventory Allocation

A sporting goods retailer rebuilt inventory allocation with ML across 180 stores. Stockout-driven lost sales down 32%; markdowns down 18%.

May 9, 2026 · 2 min read · By admin

At a glance

Industry: Retail
Topics: AI / ML · Predictive Analytics
Published: May 2026
Headline outcome: 32% Stockout-driven lost sales: down 32%

Measured outcomes

What this programme actually delivered.

32%

Stockout-driven lost sales: down 32%

18%

Markdowns: down 18%

22%

Inventory turn: up 22%

180

180 stores + 14 product categories on ML allocation

The challenge

A sporting goods retailer allocated inventory using rules-based heuristics + planner intuition. Result: stockouts on hot items, overstock on slower-moving SKUs.

What we built

ML-based allocation models considering demand patterns, weather, local-team performance, and seasonal cycles. Per-SKU + per-store granularity. Continuous retraining.