What is store analytics? Five data sources
Store analytics turns what happens in a physical store into data. The five data sources, the question each one answers, and where to start.
People counters, heatmaps, shelf recognition, product interaction: the category covers very different systems. What each one answers, the questions that separate vendors, and how to set up a fair pilot.

Decide first what you need to know: how many people came in, where they walked, what is on the shelf, or what shoppers did with the products. Each is a different kind of system. Most disappointments come from buying one while needing another.
| Type | Answers | Does not answer |
|---|---|---|
| People counting | How many visitors came in, and when | What they did with the products |
| Heatmaps and paths | Where people walked and stopped | Which product they picked up |
| Shelf recognition | What is on the shelf: stock, planogram, share of shelf | What shoppers did with the products |
| Product interaction (GoTrack) | Which products are picked up, held, put back and compared | Whether a sale followed, unless joined with your sales data |
No special AI camera is needed: the AI runs in GoTrack's software on the store device. Standard IP cameras (RTSP, ONVIF) or USB webcams with good enough image quality do the job; we can supply them if you prefer. What matters is placement: to see the products clearly and correctly, a camera sits at the right distance from them, not too close and not too far, and we choose the spot together during setup. Ceiling security cameras are usually too far from the products to see what is in a shopper's hand.
Cameras and a store device to the specification we set for your project: cameras that see the products clearly (standard IP or USB, supplied by us or bought to the spec), a small device in the store that processes the images, and an internet connection for the panel and reports. Screens are optional. The panel is used from a web browser.
Yes, through webhooks and exports. Each product interaction can be sent to your endpoint as a webhook signed with HMAC-SHA256, and every report can be exported as CSV or PDF. There is no ready-made ERP, POS, loyalty or CRM connector.
Recognition, screens and event recording carry on in the store. Screens play their stored content, and events wait on the device and are sent with their real times when the connection returns. In our test on 4 September 2026, every showing during a 7-minute outage reached the screen and its record reached the cloud afterwards.
Remotely. New versions reach store devices without a site visit, are applied at a quiet moment, and roll back on their own if the new version does not work.
Ask us every question on this page; we answer in writing.
or write to info@gotonom.com