AI System for Preparing Warehouse Slotting Candidates

The problem

In day-to-day operations, unsuitable placement can create picking and safety issues. When product dimensions and weight, movement frequency, storage rules, shelf capacity and available locations are scattered across sensors, documents, field records or team files, issues may not become visible in time.

This fragmented data delays preparation of the shelf-slotting candidate list and forces teams to search manually for supporting evidence again. The warehouse manager and occupational safety officer must complete missing records and verify each conflict before making a decision.

A common exception is that a temporary campaign or quarantine area may alter the normal layout. Incomplete or incorrect automation that fails to check this context could place a product on an unsuitable or unsafe shelf, so no physical or operational action can be carried out directly.

What we set out to improve

• Proportion of location candidates rejected by the warehouse manager
• Proportion of outputs corrected or rejected by the warehouse manager and occupational safety officer
• Time between the source event and the review output

How the system works

1. 01 Define the review scope and the roles of the authorised warehouse manager and occupational safety officer
2. 02 Retrieve the inputs: product dimensions and weight, movement frequency, storage rules, shelf capacity and available locations
3. 03 Check source identity, date, calibration or version, and data recency
4. 04 Match product constraints with shelf constraints
5. 05 Rank suitable locations by operational proximity
6. 06 Check for exceptions: a temporary campaign or quarantine area may alter the normal layout
7. 07 Place low-confidence or conflicting records in a separate specialist queue
8. 08 Write the source identity, rule, output and timestamp to the audit trail
9. 09 Have the warehouse manager and occupational safety officer approve, correct, defer or reject the output

Methods we used

• Strict capacity and compatibility filters, followed by ranking only for suitable candidates
• Source, format, timing and required-field checks for product dimensions and weight, movement frequency, storage rules, shelf capacity and available locations
• A missing-data warning instead of an estimate when inputs are incomplete or conflicting
• A separate exception check outside the main rule
• Combined retention of the source, rule result, shelf-slotting candidate list and human decision

Where people stay involved

Data and security

Access to product dimensions and weight, movement frequency, storage rules, shelf capacity and available locations is restricted to the minimum permissions required for the task. Commercial, location and employee information is masked where possible, and only the necessary portion of the dataset is sent to the model. Access, outputs and the decisions of the warehouse manager and occupational safety officer are logged; production use does not begin until the organisation has approved the retention period and data location.

Who this suits

Frequently asked questions