Is shoplifting spreading like a pandemic?
Shoplifting in the UK is spreading like wildfire. With an average of 1300 offenses reported per day in 2024, retail crime is up by 29% as compared to the previous year. The average of two incidents of retail theft every minute makes the retail companies as well as the government a worried lot (see news).
Over the past few years, several law enforcement initiatives have been launched in the UK – including increase in the number of police personnel and even a commitment to attend to all types of thefts. Even the shoplifting threshold has been done away with to ensure that police officers take up every complaint of burglary with the required level of attention.
Is this a UK-only problem?
What comes as a surprise is that this is happening in a highly monitored and regulated market such as the UK. But can this be considered as something very local to the UK or should there be a broader analysis of the situation in the European region and the US?
Are such incidents being underreported in their respective markets? Do the retailers in other regions of Europe and US have means to identify and report retail theft and violence? Are law enforcement personnel in such geographic regions equipped to take on such a herculean challenge, considering the billions of dollars of retail shrinkage being reported by industry analysts and observers?
Identifying the source – taking a leaf out of airline security
Passenger safety is at the very core of the airline industry and even though most passengers fret and fume their way through the security procedures, they do recognize and follow these steps meticulously as it impacts their personal safety. This is a classic example of preventing safety issues right at the source – the weakest link for airline security is the passengers and what they carry in their baggage.
Similarly, for any anti-theft initiative to be effective, it is vital to identify the source of the problem and to take proactive actions that can reduce the occurrence of theft.
Different forms of theft in retail
Theft in retail comes in different forms. Ranging from concealment of items, item stacking, item swapping, incorrect or incomplete scans, to part-payment, non-payment, and cart pushouts, the list is long. While on the face of it, tackling such a wide variety of theft is challenging, by focusing on the source of theft can ease the task of setting up an effective defense to prevent incidents.
Aisle theft
Shoplifting starts with items which are taken from the shopping aisles and concealed in clothing or bags. In some cases, customers just pick up the item and don’t conceal or even fill the basket or trolley and walk straight out of the store.
Self-checkout
Self-checkout, launched with much fanfare, was supposed to ease the shopping experience for genuine shoppers and reduce the manpower needs of retail companies. However, it turns out now that SCO counters account for 20% of retail theft. Here are a few patterns that SAI Group’s visual AI solution has identified at SCO counters:
- Incorrect scans: The customer deliberately weighs lower priced products instead of items that are priced higher.
- Item or product switching: The customer scans a lower value item and places another item in the bag.
- Missed scans: The customer fails to scan items from the cart or moves items over the scanner in such a way that they are not scanned.
- Non-payment: The customer walks out without finalizing the payment for the items scanned.
How SAI Group’s Visual AI can prevent retail theft
SAI Group’s visual AI is a comprehensive solution that identifies suspicious customer activity in the aisles and at the counters and alerts the store security and staff who can quickly intervene and prevent shoplifting.
| Type of Theft | How Visual AI can Prevent Theft |
|---|---|
| Concealment | Detect the customers who are concealing items in their clothing or bags. |
| Pure Theft | Detect a combination of the following types of theft:
|
SAI Group's Visual AI solution offers the following automated, timely interventions:
- Send alerts to the store staff over their handsets or the terminal when:
- Items are mis-scanned
- Some items in the cart are not scanned.
- Items are stacked and only the top one is scanned. - Display a warning message on the monitor located above the SCO stating that some issue has occurred, and that the activity is being monitored.
- Display a warning message on the SCO screen stating that a suspicious action has been recorded and give the option for the customer to take corrective action using SAI Nudge.
SAI Group's Visual AI solution boosts customer satisfaction through self-correction, cuts wait times, and eases staff workloads. It also effectively reduces shrinkage at self-checkout counters. Our streamlined AI is cost effective and scalable – and is trusted by the best retailers.
If you are responsible for retail loss prevention and if you are based in Europe or US, talk to us at the earliest about ways to tackle retail shrinkage and unruly customers. We have developed extensive analytics on consumer behavior and can help you take robust, preventive actions to ensure that your retail stores can become self-sufficient in identifying and stopping retail crime – as and when it happens.
SAI Group provides Visual AI, data analytics, intuitive dashboards, and robust reporting capabilities to three of the top retail companies in the UK. Contact us today, if you are on the lookout for a Visual AI solution that provides almost immediate return on investment.
About SAI
As a leader in computer vision technology, SAI Group delivers cutting-edge, multi-modal AI solutions into retail environments. Using a unique platform approach, its technology uses existing camera systems to target losses, increase store safety, and underpin operational efficiencies.
All solutions are built from the ground up to ensure the highest levels of security and data protection, respecting the privacy expectations of the public and operating to stringent ethical standards while delivering substantial value to our clients. Globally, SAI monitors millions of transactions per day, protecting the revenues from tens of millions of product sales and hundreds of millions of customer interactions. Its models also accurately identify anti-social behaviour, aggression and violence, helping to de-escalate situations with real-time interfaces to security officers and operations centres.
