News | April 14, 2008

Loss Prevention: Big Y Foods, Inc., Pilots New Technology To Address Checkout "Sweethearting"


Big Y has installed StopLift Checkout Vision Systems' video recognition software to catch "sweethearting", a practice which occurs when cashiers pretend to scan merchandise but deliberately bypass the scanner, thus not charging the customer for the merchandise. The customer is often a friend, family member or fellow employee working in tandem with the cashier.

Retail store employees steal $20B worth of merchandise a year, an estimated two thirds of that or $13B through sweethearting.* Supermarkets, with their especially thin profit margins, are particularly vulnerable to sweethearting, which has accounted for an almost 35% profit loss industrywide.

"We expect to have control over far more of our shrink and loss through the use of this emerging technology," said Mark Gaudette, Director of Loss Prevention at Big Y. "StopLift will enable us to improve our cashier work force through better training as well as better systems to detect and control employee theft."

"While we have loss prevention technology throughout our stores, StopLift's is the first technology to address sweethearting," Gaudette said.

Big Y is the most recent in a growing list of retailers and supermarkets, including chains such as Hannaford and Safeway, who are installing and/or piloting StopLift's technology.

The software monitors existing security cameras watching over the checkout registers. (Security cameras are at best sporadically monitored.) As soon as a "sweethearting" incident occurs, the software, which constantly monitors 100% of the security video, flags the transaction as suspicious. It quickly reports the incident, identifying the cashier and the date and time of the theft.

"If you can't sell more in this economy, you can at least take steps to lose less," said Malay Kundu, CEO of StopLift, headquartered in Bedford, MA.

To see a video of sweethearting, go on

StopLift's patent-pending computer vision technology visually determines what occurs during each and every transaction to immediately identify fraud at the checkout, according to Kundu. Dishonest associates are identified on the basis of video evidence the very first time they conduct a fraudulent transaction, rather than months or even years down the road, significantly reducing inventory shrinkage, deterring future theft, and boosting profitability.

Furthermore, the software identifies training opportunities for associates, resulting in fewer errors and improved employee retention.

The technology eliminates costly, time-consuming human review of video, drastically reduces and deters fraud at the checkout, and significantly improves profitability, Kundu said. Rather than take a one-size-fits-all approach, StopLift develops targeted applications to address the specific needs of retailers from different sectors including general merchandise, grocery, and specialty retail.

Retailers have tried to track theft through data mining, but, as Kundu notes: "Since the sweethearted item is not scanned, there's no data to track it. How do you do data mining when there's no data?"

According to the 2006 National Retail Security Survey*, 47% or nearly half of the $41.6B retail theft is committed by employees, compared to 32% by shoplifting, 18% by vendor and administrative errors, and the remainder unknown. That means employee theft at retail stores is almost 50% more prevalent than shoplifting! Big Y is one of the largest independently owned supermarket chains in New England. Proud to be family owned and operated, the company currently operates 58 stores throughout Connecticut and Massachusetts with more than 9,800 employees. Founded in 1936 by brothers Paul and Gerald D'Amour, the store was named after an intersection in Chicopee, Massachusetts where two roads converged to form a "Y".

StopLift Checkout Vision Systems grew out of Kundu's Harvard Business School research study "Project StopLift" on Retail Loss Prevention. With technological research insights Kundu developed while at MIT, Project StopLift concluded that video recognition could be used to automate and, thus, make possible the comprehensive examination of surveillance video. Prior to founding StopLift, Kundu developed facial recognition systems for identifying terrorists in airports.