New Technology Catches Theft Of Items Left In Shopping Carts

Retailers can now use their existing overhead cameras to detect the growing theft of unpaid items left in the shopping cart at the checkout.

StopLift Checkout Vision Systems has created the first technology to catch unpaid merchandise left in either the middle of the basket (MOB) or bottom of the basket (BOB). StopLift is a pioneer in detecting retail loss through "sweethearting", when cashiers fail to scan merchandise or charge the customer for it.

Until now, StopLift's video recognition technology has been detecting the sweethearting of unscanned items on the conveyor belt. Now the technology, which works with existing overhead cameras, can address MOB and BOB retail theft.

Retail theft is the fastest growing crime in America, according to the FBI. Retail store employees steal $20.3 billion worth of merchandise a year, $13 billion of it due to "sweethearting" at the checkout*. Sweethearting contributes to the growing cost of food, which the Department of Agriculture reports is at a 20-year high.

Cashiers often overlook MOB and BOB items in the shopping cart, sometimes deliberately. Reasons include sweethearting for friends as well as long lines of impatient shoppers, pressures on cashiers to work more quickly, and distracted cashiers or customers.

Where as BOB shrink is limited to bulk items like cases of water or boxes of detergent, MOB items can be anything from meat, vegetables and milk to bulk items like cereal and paper towels. Supermarkets and wholesale clubs, with their lower profit margins, are particularly vulnerable to sweethearting, which has accounted for an almost 35% profit loss industrywide.

Less than 1% of store video is actually viewed, according to Malay Kundu, CEO of StopLift Checkout Vision Systems, headquartered in Cambridge, MA. Thus, retailers have had no means of detecting MOB and BOB theft.

"By using existing overhead cameras, rather than requiring the purchase of new dedicated hardware, our technology enables retailers to address this present and growing problem," Kundu said. "Retailers are being hammered by the economy and losing more to employee theft. This new technology is giving them a foolproof means of reducing their losses."

Supermarket chains like Safeway, Hannaford and Big Y have installed StopLift's technology. Big Y, headquartered in Springfield, MA, has begun implementing StopLift throughout its 56-store chain.

StopLift's computer vision technology - patent-pending in more than 30 countries - visually determines what occurs during each and every transaction to immediately identify fraud at the checkout. In the process of monitoring100% of the security video, it flags the transaction as suspicious and quickly reports the incident, identifying the cashier and the date and time of the theft.

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.

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.

"Malay Kundu is truly a visionary in addressing sweethearting," said Mark Gaudette, Director of Loss Prevention at Big Y. "This type of theft has been costing the retail industry $13 billion a year and, before StopLift technology became available, there had been no way to detect it. With the new MOB and BOB capability, we can significantly reduce our shrink.

"In addition, StopLift will enable us to improve our cashier work force overall through better training as well as better systems to detect and control employee theft," Gaudette said.

Retailers have traditionally tried to track loss at the checkout through data mining, but since MOB, BOB and other sweethearting involve items not being scanned, Kundu notes: "How do you do data mining when there's no data?"

According to the 2006 National Retail Security Survey*, 47% or nearly half of retail theft is committed by employees, compared to 32% by shoplifting. That means employee theft at retail stores is nearly 50% more prevalent than shoplifting.

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.

* The National Retail Security Survey reports that $41.6 billion was stolen at U.S. retail stores in 2006. The survey is a collaborative effort between the National Retail Federation and the University of Florida.

SOURCE: StopLift