Detect Loss Early

Shrinkage starts with behaviour. Detect suspicious activity in real time, capture evidence, and act immediately, without requiring full-store coverage.

Before It Becomes Loss

Conventional shrinkage reports only reveal what has already happened after the fact. We identify suspicious behaviour in real time, enabling immediate response, evidence capture, and proactive prevention. This helps operators act early, reduce losses, and strengthen operational control across stores.

See Behaviour Live

Detect unusual activity as it happens. Monitor key zones such as alcohol, cosmetics, and self-checkout, identifying prolonged dwell, repeated handling, and concealment-like movements using intelligent triggers.

Act Instantly

Receive clear, actionable alerts. Notifications indicate where attention is needed, enabling staff to respond immediately without constant monitoring or complex interpretation, ensuring faster and more accurate operational decisions.

FootfallCam Act Instantly
FootfallCam Verify with Evidence

Verify with Evidence

Every alert includes a short clip and snapshot. Store teams can quickly verify situations, reducing ambiguity and enabling confident action without reviewing hours of footage or manual investigation.

Deploy Where It Matters

Focus on high-value and high-risk areas. Deploy in selected zones instead of full-store coverage, making the solution practical, scalable, and easy to standardise across locations for consistent operational efficiency.

FootfallCam Deploy Where It Matters
FootfallCam Review and Improve

Review and Improve

Review flagged events by time, zone, or behaviour. Identify recurring patterns and refine store response, improving effectiveness and operational consistency without increasing workload or management burden.

Case Study

High-value loss reduced

Self-checkout misuse controlled

Blind spots eliminated

High-value loss reduced

Case Study 1

High-value loss reduced

Store size

9,200 sq ft supermarket, urban location, high-value alcohol and cosmetics sections

Loss issue

Shrinkage concentrated in alcohol aisle during evening hours. Incidents were inconsistent, with no clear visibility on when or how losses occurred.

Deployment scope

Queue Control Suite deployed across all checkout points. Real-time monitoring, 15-minute prediction, and standardised action thresholds enabled.

Behaviour detection deployed in alcohol and cosmetics zones. Real-time alerts and clip-based evidence enabled immediate staff response and structured review of suspicious events.

Measured improvement

Suspicious behaviour incidents reduced by 35% within 6 weeks. Staff presence increased during peak periods, and repeat loss patterns in alcohol section were significantly reduced.

Self-checkout misuse controlled

Case Study 2

Self-checkout misuse controlled

Store size

7,800 sq ft supermarket, suburban location, 4 staffed lanes + 8 self-checkout kiosks

Loss issue

Frequent misuse at self-checkout, including non-scanned items and irregular scanning behaviour. Staff were unable to monitor all kiosks effectively during busy periods.

Deployment scope

Monitoring deployed across self-checkout zone. Alerts triggered on prolonged dwell, repeated item handling, and irregular interaction patterns, supported by clip-based verification.

Measured improvement

Unresolved self-checkout discrepancies reduced by 28%. Staff intervention improved, with faster response to flagged behaviour and more consistent supervision during peak hours.

Blind spots eliminated

Case Study 3

Blind spots eliminated

Store size

11,500 sq ft supermarket, neighbourhood store with partial CCTV coverage

Loss issue

Shrinkage reported across multiple categories, but CCTV coverage was incomplete. Investigation relied on manual review with limited success in identifying causes.

Deployment scope

Targeted deployment in key aisles with historically high loss. Behaviour detection and event capture enabled structured review without requiring full-store coverage.

Measured improvement

Investigation time reduced by over 60%. Store teams identified recurring patterns in specific aisles, leading to improved staff allocation and reduced repeat incidents.