At the International Security Conference & Exposition (ISC West) today, DeepCam introduced Retail by DeepCam, a plug-and-play system that reportedly improves retail loss prevention and slashes operational costs through a proprietary biometric-enhanced recommendation engine that identifies shoplifting and other suspicious behaviors.
Developed by an AI team with more than 200 years of combined experience, DeepCam has reportedly succeeded in international trials and with select US retailers. Based in Longmont, CO, DeepCam’s system achieves the large-population performance required in public safety and multi-location retail and banking applications.
“When you have a small population, such as an office building, facial recognition is easy,” said Don Knasel, DeepCam founder and CEO (shown). “Where biometrics fail is with large populations—tens of thousands or hundreds of thousands of people—and that’s what sets our AI technology and recommendation engine apart. Our systems have been proven in international trials to work accurately with large populations.”
Retail by DeepCam is designed specifically for multi-location stores, which may already have some kind of loss prevention system but likely miss the vast majority of shoplifters. The DeepCam AI system looks for shoplifting and other suspicious behaviors that indicate further attention.
This results in a list of people of interest for loss prevention to review, tagging those to who should not be allowed back. Then the system notifies store employees, allowing managers to stop the criminal and ban them from entering again.
“Some stores may catch as little as 10 percent of shoplifters,” said Knasel. “Our system not only catches that 10 percent, but is designed to drastically close the gap on what other systems miss.”
The system uses four proprietary technologies: biometric identification for large populations, cross-camera event association to understand movement within a store; multi-location data analytics; and behavior analytics.
A technology and big data analytics system that goes beyond loss prevention, DeepCam also delivers wide-ranging retail intelligence that can be used for customer appreciation, merchandising optimization and operations improvement. Retail by DeepCam can identify everything from the number of customers at a given time or day, queue wait times, and shopping habits by demographics and location.
After the completion of extensive trials with large retailers in the United States and in public safety settings abroad, DeepCam began shipping in Q4 2017. In the US market, Retail by DeepCam began to roll out in Q1 of this year.
