Visualizing missed-sale opportunities overlays POS sales data onto the shelf allocation, letting you check "which item at which position is selling" as if looking at a map. You can intuitively grasp the relationship between placement — gondola end, edge, lower shelf, and so on — and sales.

Shelf heat map

Each position on the shelf is displayed with a color intensity representing sales, sales quantity, or profit.

• Dark color = high sales / light color = low sales
• You can grasp sales bias by shelf row and left-right position at a glance
• You can switch the period (daily, weekly, monthly) to compare

ABC analysis

Items placed on the shelf are ranked A (top), B (middle), or C (bottom) based on their sales contribution.

• A-rank items — core items that account for 70% of sales. Gondola-end placement is recommended
• B-rank items — moderately contributing items that account for 20% of sales
• C-rank items — lower-tier items that account for 10% of sales. Candidates for discontinuation

Position × sales matrix

You can discover "items in a good position that aren't selling" and "items in a poor position that are still selling."

• C-rank items at the gondola end → consider swapping placement
• A-rank items on the lower shelf → consider promoting them to the gondola end
• You can also analyze whether sales increase when combined with adjacent items

AI-driven placement suggestions

An AI trained on sales data, category, and customer flow data generates placement change suggestions.

• Specific suggestions such as "swapping Item A and Item B is projected to increase sales by +8%"
• You can apply a suggestion to the shelf allocation plan with one click
• Verify the effect with an A/B test

Period comparison

Compare sales before and after a shelf allocation change to quantify the effect of the change. This can also be used for seasonal item rotations or evaluating a temporary campaign display.

Related articles: What Is Shelf Analytics? | Product Placement Management | Shelf Performance Analytics