Beating self-service checkout theft
The solution to self-service checkout theft might have been solved by Scottish researchers.
Abertay University academics found digital human-like faces at supermarket self-service checkouts can help reduce the risk of shoplifting.
The study simulated a self-service checkout scenario, with participants asked to scan and weigh items before making the final payment.
Opportunities were provided in which shoppers could benefit financially through dishonest behaviours.
"Items without a bar code provided opportunities for dishonest behaviours as participants were required to select a weight or provide item numbers," researchers wrote.
They found when a human-like face was present, participants were less likely to cheat the system than times it was not included.
"This study shows that there are potential effects on people's behaviour due to the inclusion of human-like elements within the service," explained researchers.
"Interface designers interested in this field need to achieve a balance in that an agent will have to be noticed sufficiently, while not interfering with a consumer's task."
Researchers concluded there is "huge merit in maintaining a social element in consumer interaction with technology" when focusing on reducing self-service checkout theft.
The study comes as retailers across the country currently are trailing several different methods to combat self-service checkout theft.
Several unnamed supermarkets in New South Wales are currently working with Melbourne robotics firm black.ai to create sensors which create a log of the products the customer selects - this information is input into the checkout at the time of purchase.
"Our distributed decision-making stack maintains a virtual 'cart' for each customer, reliably detecting and tracking all product interactions," black.ai previously told nine.com.au.
Australian company Tiliter Technology has also developed a similar automated product recognition system which relies on machine learning and artificial intelligence.
The company uses a camera to identify the product and then automatically enters the information into the point-of-sale system – it claims to be able to tell the difference between varied products from the same family such as Red Delicious, Fuji, Pink Lady and Royal Gala Apples.
Earlier this year, a select number of Coles stores across Victoria also installed cameras directly above the self-service monitor, with every move made at the checkout broadcast back to the shopper and recorded on file.