Shoplifters cost stores billions. UF professor explains how AI can help fight store theft and fraud – News


A University of Florida professor will speak on Wednesday at Nvidia T & Cs, one of the world’s largest technology conferences dedicated to artificial intelligence.

Read Hayes, Ph.D., is a world-renowned expert on the science of theft in department stores and grocery stores. Based at FLEX at the Herbert Wertheim College of Engineering, he works with professors of engineering and computer science to help design programs to identify shoplifters. He is also director of the Loss Prevention Research Council, which works with more than 70 major retail chains providing them with innovative loss and crime control solutions.

At GTC on Wednesday, Hayes will be among five panelists who will explain how artificial intelligence programs, such as Already seen, can reduce intentional and accidental loss of inventory at cash registers and self-checkout terminals.

Hayes provided his expertise to Eversen to help their AI identify behavioral cues from someone having trouble scanning an item at a self-checkout terminal, intentionally scanning items incorrectly, or failing to scan any articles at all. The program was recently rolled out to Kroger grocery stores nationwide.

“My job was to help them narrow down all the ways people can make a mistake during a self-checkout,” said Hayes. “The models are designed to recognize someone who is not scanning correctly. “

In 2019, theft, fraud and loss totaled $ 61.7 billion, according to the National Retail Federation Annual National Retail Safety Survey, which was released in July. Theft and fraud are not only costly for businesses, but they can also be dangerous.

Hayes, who worked as a part-time detective in a department store while in school, has first-hand knowledge of the dangerousness of meeting a shoplifter. Over 30 years ago, he and a store manager attempted to confront a trio working together to steal clothes. It got out of hand quickly. The confrontation ended with the involvement of at least half a dozen officers.

“I still have scars on my hands,” Hayes said of the incident. “People don’t like to get caught.

That’s why the best way to prevent theft or fraud is through deterrence, said Hayes.

When programs like Everseen identify someone who is not scanning properly, they can stop the transaction and ask a staff member for further help. In addition, a video appears on the screen replaying the wrong scan, which makes it more difficult to dispute the incident if it is intentional.

Being filmed and immediately confronted with the video would ideally prevent someone from trying to steal again.

“We can’t change their lives,” Hayes said. “But if we can convince someone not to steal or do anything wrong, then we’ve done our first job.”

The panel will include executives from Everseen, Kroger, Lenovo and Omni Talk. “The AI ​​retail use case that stands out from the crowd»Will start this Wednesday at 11 am

Cynthia Roldán Hernández November 9, 2021


Comments are closed.