Indivd
•
•
Intro
A watch and jewellery store in Northern Europe achieved 99.42% absolute people-counting accuracy. A video review of 859 entries and exits checked the visitor counts behind conversion calculations and staffing decisions.
A fine watch and jewellery retailer in Northern Europe had Indivd’s people counting checked at one store using samples collected from 25 to 28 September 2026.
Across eight counting lines on four cameras, manual video review identified five counting errors in 859 entries and exits. The combined result was 99.42% absolute counting accuracy.
The store
When a few counts can change the picture
A visit to a watch and jewellery store might involve choosing a ring, collecting a serviced watch or considering a first major purchase. For the retailer, understanding how those visits translate into transactions starts with knowing how many people came through the door.
During quieter periods, each visit represents a larger share of the total. A small counting error can therefore have a greater effect on reported conversion.
An undercount makes conversion look higher without any additional transactions. An overcount makes it look lower. Before interpreting a change in store performance, the team needs to understand the reliability of the visitor count behind it.
At this location, the assessment covered four camera positions, each with an entry and an exit counting line.
The check
Eight counting lines, five recorded errors
Indivd checks counting accuracy against manually reviewed video of real store activity. Reviewers examine masked footage frame by frame, count entries and exits, and compare those observations with the automated counts for each counting line.
The process allows customers to choose the locations, periods and amount of testing, and to arrange for a third party to carry out the check without Indivd present. This gives retailers a way to test performance under conditions relevant to their own stores.
Indivd’s documented verification process explains the manual checks, report fields and accuracy calculations. Customers and their appointed reviewers can examine the method and supporting results to understand how a percentage was reached.
At this watch and jewellery store, the assessment covered eight counting lines on four cameras.
DEFINITION
Absolute accuracy is 100 percent minus the absolute error rate.
Undercounts and overcounts are both errors. A missed entry, a missed exit, and a counted person who never crossed are each counted in full. Errors in opposite directions are never permitted to cancel one another.
What the number carries
A checked visitor count behind retail decisions
The result gives the retailer a documented check of counting performance across all eight assessed lines.
When teams calculate conversion, plan staffing around visitor demand or assess traffic during an event, the visitor count helps shape their interpretation. Checking that count provides evidence about the measurement behind those decisions.
It also helps separate two questions: did store performance change, and how reliable is the data used to measure it? The QA review addresses counting accuracy. Transactions, sales and staffing outcomes need to be assessed alongside the retailer’s own trading figures.
The 99.42% result is the combined accuracy across the eight counting lines during the sampled periods. It provides a verified reference for the assessed setup.
The method can also be checked by a third party
In a separate customer-commissioned review, KPMG applied Indivd’s quality-assurance methodology and recorded approximately 99% absolute counting accuracy. KPMG carried out the review using Indivd’s method. This was a separate engagement from the watch and jewellery assessment reported here.
For retailers evaluating suppliers, knowing who commissioned a review, who performed it and which method they used helps make accuracy claims easier to assess. These distinctions are explained in Indivd’s guide to testing people-counting accuracy claims.
Common questions
How do you measure conversion in a watch and jewellery store?
Store conversion is commonly calculated by dividing the number of transactions by the number of visits, then multiplying by 100. An undercount of visits raises the reported conversion rate; an overcount lowers it. Accurate visitor counts help retailers interpret conversion alongside sales and transaction data.
Why does footfall accuracy matter during quieter trading periods?
When there are fewer visits, each visit represents a larger share of the total. A handful of counting errors can therefore have a greater effect on reported conversion. Checking footfall accuracy helps teams assess whether the visitor data is reliable enough to support their comparisons.
What should a watch and jewellery retailer look for in a people-counting accuracy report?
Look for results from a comparable store environment, a clear definition of accuracy, the number of entries and exits reviewed, sampling dates and the verification method. Check whether the headline describes a combined result, an average or a minimum across locations.
Can a third party verify Indivd’s counting accuracy?
Yes. Indivd’s verification process allows customers to choose where, when and how much to test, run checks without Indivd present and appoint a third party to carry out the review. Automated counts are compared with manual video counts using a defined accuracy measure.