Shelf interaction and shopper behaviour analytics
Shopper behaviour analytics measures how store visitors interact with shelves and products, using camera video. EscherSense counts picking a product up, examining it and putting it back as separate events, and anonymously reports how many passers-by look at your window, the mix of family and solo shoppers, and when shelf layouts drift out of order.
A shopper who stops at the shelf and walks away empty-handed is never recorded anywhere. Your till report shows what sold, not what drew interest and still failed to sell. Yet a product that keeps going from hand back to shelf may be telling you something about its price, packaging or product information.
Looking is not the same as touching. Behaviour analytics measures that difference to reveal genuine interest, adding shelf-level meaning to the density shown by your retail heatmap.
How it works
Shelf and window zones
The shelves, tester areas and window frontage to be measured are defined as zones on the camera view.
Micro-gesture detection
Picking up, examining and putting a product back are each detected as distinct events.
Interest and segment analysis
Interactions are aggregated by zone, and shopper segments are inferred from cues such as group size.
Shelf tidiness tracking
The model learns what a well-kept shelf looks like and alerts staff when disorder passes the set threshold.
What it measures
Product interaction rate
The share of shoppers stopping at a shelf who actually touch a product.
Pick-up to put-back ratio
How often products are picked up and returned; can flag something blocking purchase despite interest.
Shelf dwell time
Average time spent in front of a given shelf or category.
Window effectiveness score
The share of passers-by who look at your window; measures the return on visual merchandising.
Segment mix
The share of family and solo shoppers, based on cues such as prams, bags and group size.
Shelf tidiness score
How far the current shelf has drifted from its learned ideal layout.
In-store use cases
Tester areas in cosmetics
Footfall at the tester unit and actual product trials are measured separately. Products that are tried often but rarely bought stand out, prompting a review of price, stock or advisor support.
The comparison moment in electronics
When a shopper keeps moving between two products, that is the moment they need help. Shelf dwell time makes these moments visible so staff can step in at the right time.
Window and department interest in fashion
The share of passers-by looking at the window is tracked alongside product interaction inside. You can compare which window displays and which departments really draw attention.
Getting promoted products noticed in grocery
Measure whether a promoted product is actually being handled on the shelf. When the shelf falls out of order, a tidiness alert sends staff to fix it.
Privacy and GDPR/KVKK
Behaviour analytics measures movement; it does not recognise people. There is no facial recognition and no identity matching, and segments are inferred in aggregate only from visual cues such as group size, prams or shopping bags. Reports show totals by zone and category, never individual records. By default, video is processed on a server inside the store and raw footage never leaves the premises; if your IT policy prefers, processing can run in the cloud instead. Retention periods are defined, and the setup is designed around KVKK and GDPR requirements.
Setup and integration
Behaviour analysis needs a camera angle with a clear view of the shelf or window zone being measured; we assess which spots your existing cameras cover free of charge before installation. ONVIF-compatible IP cameras with an RTSP stream are supported. Interaction and alert data is sent via REST API and webhooks to ERP, CRM and BI tools in JSON and CSV formats.
Frequently asked questions
What does shopper behaviour analytics measure?
Shopper behaviour analytics measures the physical interaction between shoppers and shelves or products. Pick-ups, examination and put-backs are counted as separate events, and window engagement and segment mix are reported too. Measured accuracy for behavioural analysis is 95.4%.
Why does the difference between looking and touching matter?
Because genuine interest starts with touch. Walking past a shelf is not interest, while picking up and examining a product is much closer to purchase intent. This distinction lets you find products that attract attention but fail to sell.
What is a window effectiveness score?
A window effectiveness score is the share of people passing your storefront who actually look at the window. Different window displays can be compared on the same measure. Read together with capture rate, it shows how the window affects traffic.
Does segment analysis need to identify shoppers?
No, segment analysis uses no identity information. Family and solo shoppers are distinguished by visual cues such as group size, prams and shopping bags. Results are reported only as aggregate shares.
How does the shelf tidiness score work?
The model first learns the shelf's ideal appearance, then scans the current shelf at regular intervals. When deviation exceeds the set threshold, the relevant staff get an alert. If the alert goes unanswered, it escalates to the next level.
How does behaviour data help with promotions?
Behaviour data shows whether a promoted product is noticed on the shelf and whether it is actually handled. Read alongside traffic and conversion, it pinpoints the stage at which a promotion loses shoppers. See campaign analytics for more.
Related modules
Retail heatmaps and customer path analysis
A retail heatmap is a colour-coded view of how much time shoppers spend in each zone of the sales floor. EscherSense builds it anonymously from your existing ceiling cameras, and its path analysis reveals the most common routes from entrance to checkout, movement between aisles and the dead zones that almost nobody visits.
Explore module →In-store campaign performance and ROI measurement
Retail campaign analytics measures the separate effect of an in-store campaign on visitor traffic, product engagement and conversion rate. EscherSense compares these three indicators before, during and after the campaign on the same metrics, and combines them with POS data to show the campaign's real return on investment by store and across the chain.
Explore module →Anonymous demographic analytics: visitor age and gender mix
Retail demographic analytics is the statistical estimation of visitors' age band and gender from camera video. EscherSense does this without identifying anyone, without storing face images and in line with KVKK and GDPR. The output is never a personal record, only hourly and daily aggregate distributions your store and marketing teams can act on.
Explore module →