Data Science Investment Counter —Funding raised by UK data science companies in 2018.
£ 5.640 Million

Japanese startup develops AI to spot shoplifters before they steal

CCTV Sweden Surveillance Stockholm Camera Wireless

Japanese startup Vaak has developed artificial intelligence (AI) software that looks for potential shoplifters using footage from security cameras and reading potentially suspicious body language.

The algorithms analyse security camera footage and alert staff about potential thieves via a smartphone app before the crime will take place.

The goal of this new AI, according to Vaak, is prevention. If the target is approached and asked if they need help, the company said, chances are that will stop the thief from stealing in the first place.

The technology has already been tested successfully in a convenience store in Yokohama last year. The wrongdoer who was spotted by the Vaak software was apprehended and arrested by police a few days later.

“I thought then, ‘Ah, at last!’” said Vaak founder Ryo Tanaka. “We took an important step closer to a society where crime can be prevented with AI.”

According to a report by Tyco Retail Solutions, shoplifting cost the retail industry about $34 billion in lost sales in 2017. And data from Gartner Inc has shown Retailers are projected to invest $200 billion in new technology in 2019.

With this data in mind, companies like Vaak with software capable of meeting retailers’ needs for security are going to be highly sought by retail companies.

“If we go into many retailers whether in the US or UK, there are very often going to be CCTV cameras or some form of cameras within the store operation,” said Thomas O’Connor, a retail analyst at Gartner.

“That’s being leveraged by linking it to an analytics tool, which can then do the actual analysis in a more efficient and effective way.”

AI technology is already being deployed by retailers to help them do business. These applications include inventory management, delivery optimisation but also customer-support chatbots on websites and image and video analysis.

But Tanaka is also planning other applications of his software, outside retail. For example, he said, Vaak AI could be deployed in public spaces and train platforms to detect suspicious behaviour or suicide jumpers. 

“We’re still just discovering all the market potential,” Tanaka said. “We want to keep expanding the scope of the company.”

Vaak was founded in 2017 and is currently testing its software in some shops in Tokyo. The company started selling a market-ready version of its shoplifting-detection software this month and is aiming to be in 100,000 stores across Japan in three years.

It raised ¥50 million in funding from SoftBank Group Corp’s AI fund, and is now in the middle of its series A round, seeking to raise ¥1 billion.

Picture via Max Pixel.


Co-working space and blog dedicated to all things data science.

Subscribe to our newsletter