Retail theft is one of the industry’s biggest challenges, costing more than $100 billion globally each year. In the UK alone, shoplifting has risen by 13% over the past year, following a 25% jump in 2023–24 to more than 20 million incidents – the highest level since records began – costing retailers an estimated £2.2 billion in losses.
Working with several major European retailers, Trigo’s computer vision AI platform analysed more than 1,000 verified theft cases to understand how shrinkage occurs across the customer journey. The study provides one of the most comprehensive views to date of how theft takes place across the store environment.
Key findings:
- The most frequently stolen categories are beverages (22%), fresh produce (19%), and bakery items (10%)
- Concealment is widespread – only 20% of stolen items reach the self-checkout in plain view.
- When they do, thieves often use a range of tricks to avoid paying – the most common being ‘fake scans,’ where an item is waved over the scanner but not actually registered (27.3% of cases)
Theft peaks on weekday afternoons (46.6%) and evenings (30.4%), with Thursday afternoons alone accounting for 18.4% of incidents, while Saturdays see the lowest levels (4.6%)
Using its advanced AI computer vision technology to track commonly stolen products from shelf to exit, Trigo uncovered systematic concealment on an unprecedented scale. The analysis showed that 80% of targeted items were hidden in clothing or bags before reaching checkout, with only 20% appearing in plain view at the scanning area.
This means conventional security systems—designed to monitor checkout behaviour—are fundamentally misaligned with how theft of commonly stolen products actually occurs. The findings marks a shift in how the retail industry understands shrinkage, revealing that the majority of losses happen long before the checkout point.
Beyond concealment, the study also highlights what happens when items do reach the checkout. Around 20% of visible stolen items make it this far, and thieves use a consistent playbook of tactics to avoid payment.
Common tricks include leaving items in the basket or bagging area without scanning (31.7%), performing a ‘fake scan’ where an item is passed over the scanner but not registered (27.3%), or deliberately holding products back and not scanning them at all (14.1%). This behaviour is particularly difficult for staff to detect as it often appears subtle and can easily be mistaken for an honest error.
Timing patterns also revealed clear trends across stores. Nearly half of all theft occurs in the afternoon (46.6%), with evenings also proving high-risk (30.4%). Thursday afternoons stand out as the single most common window (18.4% of thefts), while Saturdays see the lowest levels (4.6%) — likely because more staff and security are present during peak trading hours.
“Most retailers today are either discovering what was stolen after the fact through inventory audits, or at best, catching visible theft at checkout,” said Daniel Gabay, CEO of Trigo.
“As theft tactics evolve beyond simple scanning avoidance to systematic concealment, the question for the industry becomes whether traditional security infrastructure can adapt, or whether AI-powered tracking from shelf to exit will become the new standard.
“By tapping into existing CCTV cameras, computer vision AI technology makes it possible to track frequently targeted products in real time from shelf to checkout, delivering total store coverage. Whether a shopper hides an item under their jacket, or skips scanning altogether – AI will detect it. As retailers look ahead, this kind of end-to-end visibility could define the future of loss prevention — where every item, in every aisle, is accounted for.”
