Fujitsu Leverages AI to Cut Retail Self-Checkout Fraud

The solution works by adding low-cost cameras to existing self-checkouts and using AI to cross-check scanned items, helping detect and prevent fraudulent barcode use by consumers. A large-scale study¹ by the UK’s University of Leicester found that retailers in Europe and the US that utilize self-service checkouts experience a shop-lifting rate nearly double compared with traditional manned checkout. By reducing self-service checkout fraud, the new Fujitsu technology holds the potential to save retailers billions of Euros annually.

Developed at Fujitsu’s AI Center of Excellence at Paris-Saclay in France, the new AI-based fraud prevention solution – part of Fujitsu’s Zinrai portfolio of AI solutions – is designed to help retailers cut losses at self-checkouts. The technology complements existing self-checkouts by cross-checking customers’ barcode scans against images from cameras fitted to already-installed scanners. The new technology is able to identify mismatches without the cost and complexity of adding graphical processing units (GPUs) to each checkout, substantially reducing the total cost of ownership and dramatically raising the return on investment.

Following development workshops with a leading European hypermarket retailer in December 2018, a pilot trial is taking place during January 2019. Following a machine learning stage, in which the system learns the key visual characteristics of any item presented at the checkout, it can tell the difference between an expensive item and a lower-cost item with the same weight, even when a barcode is transferred from one item to another. If an item’s expected appearance does not match the scanned barcode, then the self-checkout calls for a manual intervention and check. Fujitsu is also working to further develop the solution to detect additional checkout fraud methods including sweethearting, scan-avoidance and basket-based loss.

Bruno Sirletti, Vice President and Head of Retail & Hospitality at Fujitsu EMEIA, comments: “Fujitsu has moved well beyond the AI hype and is delivering real business outcomes from this promising technology. The fraud prevention solution is one of the first commercial applications that was developed in our AI Center of Excellence in Paris. This is a particularly pertinent topic for grocers, as there is typically around twice as much fraud committed at supermarket self-service checkouts compared to manned registers. However, our breakthrough technology reduces this fraud by making it very difficult to trick the checkout, and achieves this without inconveniencing honest shoppers. Through cutting fraud at self-service checkouts, grocers can take a step towards the frictionless, cashierless supermarket of the near future, while still maximizing their existing scanner investment.”

Fujitsu expects the future application of AI to create even greater efficiencies across the retail supply chain, with barcodes evolving from a simple SKU (stock keeping unit) listing to including more detailed information, such as logistics data and expiry dates. By extracting and analyzing this data, retailers can increase the efficiency of the tracking of goods, resulting in shorter, more effective supply chains and reduced losses from spoiled produce.

Availability
The Fujitsu solution is available immediately in the EMEIA region (Europe, the Middle East, India and Africa) via Fujitsu’s direct channels, with availablity in other regions expected later in 2019.

Notes for editors
¹A study of self-checkouts with handheld scanners, conducted by the University of Leicester in the UK, found evidence of widespread shoplifting, based on data from nearly 12 million shopping trips, of which one million were audited in greater detail, at major Belgian, British, Dutch and US retailers. Researchers found that introducing self-checkouts raised the rate of loss by 122 percent to an average 3.9 percent of turnover. The European retail grocery market alone is estimated by analysts IGD to have a turnover of nearly €2 trillion, implying a potential saving of approximately €80 billion.