Warehouse Slotting

AI recommends where to store items so warehouses can reslot faster and pick more efficiently.

Business impact

• Throughput — Lucas Systems says its Dynamic Slotting promises a 20-40% increase in throughput.
• Shipments per order — AEO reported shipments per order improved from 1.2 to under 1.1.
• Average package delivery distance — AEO reported average package delivery distance of approximately 100 miles.

Data requirements

• Warehouse operational data (tabular) — Used to evaluate inventory placement and movement patterns.
• SKU velocity data (tabular) — Shows how fast items move through the warehouse.
• Item size data (tabular) — Helps match products to suitable storage locations.
• Demand seasonality data (tabular) — Helps adjust slotting for changing order patterns.
• Pick-path data (tabular) — Shows how workers move through the warehouse.
• Activity-level data (tabular) — Supports prediction of task time and continuous optimization.

AI methods and techniques

• Machine learning — Recommends which products should be moved and where they should go.
• Similarity detection — Keeps related items from being placed side by side when that would raise picking errors.
• Prediction — Predicts task time from activity-level data as warehouse conditions change.

Industries

Real-world evidence

2 documented case studies on record.

Companies using this: American Eagle, Amazon.