Understand competitive presence
See how your brand’s visible facings compare with competing brands within the same category. Use the evidence to focus conversations with account and field teams.
AI SHARE OF SHELF MEASUREMENT
Share of shelf measurement.
See your brand’s place.
Share of shelf measures your brand’s presence within a defined retail category. Aislemetry uses AI to identify products in shelf photos, count their facings, and turn shelf presence into a measurement your team can review.
VISIBLE CATEGORY FACINGSILLUSTRATIVE DATA
Fictional brands and sample values. Same category scope; unresolved facings stay in the total. This graphic does not run image recognition.
QUICK ANSWER
What is AI share of shelf measurement?
AI share of shelf measurement calculates a brand’s proportion of visible category facings from shelf photos. Aislemetry detects packs, matches brands using product references, and divides brand facings by all visible category facings. Unresolved facings stay in the total, and uncertain identities need human review. Clear photos and consistent category boundaries are essential for useful comparisons.
- Inputs
- Shelf photos, category boundaries, and reference product images.
- AI process
- Count visible facings, match brands, and calculate each brand’s percentage.
- Outputs
- Brand facing counts, category totals, and shares with uncertain identities flagged.
WHAT IS SHARE OF SHELF?
A clear measure of
visible brand presence.
Share of shelf compares a brand’s presence with the whole defined category. A facings-based measurement counts the front-facing packs shoppers can see, including repeated packs of the same product.
FACINGS-BASED SHARE OF SHELF24 brand facings ÷ 60 category facings × 100 = 40%
Illustrative example.
Illustrative example.
Agree on the measure before comparing.
Choose the category, shelf area, and counting rules before capture. Include all visible category facings in the denominator, even when their brand is unresolved.
Linear-width share measures shelf width instead of pack count. Different pack sizes can produce different results, so width-based and facings-based percentages are not interchangeable. Share of shelf also does not establish sales share or market share.
FROM VISIBILITY TO EXECUTION
Know where your brand
needs a closer look.
Manual shelf measurement takes time, and inconsistent counting rules make stores hard to compare. Aislemetry connects the numbers to shelf evidence so teams can investigate the difference.
Compare a consistent category
Assess brand distribution across stores or visits using the same scope and method. Compare both facing counts and percentages to understand what changed.
Investigate execution gaps
Review shelf presence against your agreed targets. A lower share can prompt a store check; the underlying photo helps your team decide what to investigate next.
HOW AISLEMETRY USES AI
From shelf photo
to reviewable measurement.
AI supports the repetitive identification and counting work. Your category definition and product references give that work the right context.
Define the scope and capture the shelf
Select the category and measurement method. Capture clear, complete shelf photos, with a consistent approach to overlapping images and repeat visits.
Detect products and count visible facings
Aislemetry uses AI to locate visible products and count their front-facing packs. Hidden units behind those packs are outside the facing count.
Match brands and product identities
Product catalogue references help match the visible packs to brands and SKUs. Blur, glare, small packs, and partial labels can leave identities uncertain.
Calculate shares and review the evidence
Group the facing counts by brand and divide by the category total. Keep uncertain matches reviewable and unresolved facings visible before using the results.
ILLUSTRATIVE MEASUREMENT
The denominator
makes the difference.
In this fictional category, Harvest has 24 of 60 visible facings: a 40% share. The 12 unresolved facings remain in the total; excluding them would overstate Harvest’s share.
| Brand group | Visible facings | Share of category |
|---|---|---|
| Harvest | 24 | 40.0% |
| Grove | 16 | 26.7% |
| Other identified brands | 8 | 13.3% |
| Unresolved brand | 12 | 20.0% |
| Total visible category | 60 | 100% |
These are sample values, not customer results. Resolve uncertain identities before treating brand shares as final. A photo measures the visible shelf at that moment.
SHARE OF SHELF / QUESTIONS
Make the measurement
mean the same thing.
What makes shelf photos useful for AI analysis?
Clear, well-lit photos with readable packs and complete category coverage help identification and counting. Agree how to handle overlapping photos, cut-off packs, obstructions, and glare during the pilot.
How should teams compare stores or visits?
Keep category boundaries and counting rules consistent. Review the underlying counts, unresolved identities, and photo coverage alongside percentages. A change in the category total can change share even when your own facing count stays the same.
Reviewed · Aislemetry