LightHaus VCI analyzes video from in-store cameras to measure customer traffic and engagement. The system is designed to help retailers boost their sales conversion rate, or the percentage of store visitors who actually buy something.
"We take the in-store video and count what customers are doing--how many come in the store, where they go, what they stop and look at, and how long they stay there and look at it," said Virginia Balcom, Lighthaus vice president of marketing and product management, in a phone interview with InformationWeek.
[ Facebook is looking toward the future of data analysis. Read more at Facebook Seeks Next-Generation Big Data Tools. ]
Retail store conversion rates are surprisingly low. "In a specialty store, a fashion store in a mall, you might see a conversion rate of 10% to 20%. So 8 out of 10 shoppers aren't purchasing," said Balcom.
Lighthaus, a 6-year-old video analytics provider based in Vancouver, Canada, began focusing on the retail market a little over two years ago. Other retailers besides Foot Locker use Lighthaus' technology, said Balcom, who declined to name additional customers. "They view these processes as a significant competitive advantage and are quite hesitant to talk about how they use it," she said.
The VCI system uses off-the-shelf video cameras--typically digital IP cameras--that are usually mounted on the ceiling for a bird's-eye view of customer activity. "This is convenient because it gives the least obstructed view of people in the store," said Lighthaus chief technical officer Mario Palumbo.
Each store has what Lighthaus calls a "network appliance," a PC running the company's VCI software that's configured remotely. It typically sits in a back room. "From the retailers' perspective, it's a black box. They don't need to touch it," said Palumbo.
The cameras capture video and send it to the network appliance, which processes the feeds in real time. The VCI system extracts numerical metadata from the video and uploads it to Lighthaus' cloud-based server.
"Under normal operation, there's no video that ever leaves the store. This is to conserve bandwidth, but also to address some privacy concerns," said Palumbo. "If one hundred people walk in the door, we'll send the number '100' to the server. We don't need to send pictures to accompany that."
Many monitoring systems count front door traffic, but what makes the VCI system compelling is its ability to examine customer activity throughout the store, such as the number of people who stop at a particular display and how long they stay there.
Lighthaus' software can distinguish between background objects that don't move (e.g., a floor display) and human activity. "It detects when a person enters the scene, and can track that person," said Palumbo. This allows the VCI to determine the number of people who interacted with a product display.
Data from a retailer's multiple locations is aggregated on a cloud server, where Lighthaus' customers can "slice and dice it" via any Web browser, said Palumbo.
Here's an example of how Lighthaus' system could help a retailer determine its sales conversion rate: A store sells 20 pair of a new Adidas shoe on Saturday, and the VCI reports that 200 people visited the Adidas shoe's floor display that same day. The retailer then determines it had a 10% conversion rate for that particular shoe on Saturday.
Lighthaus officials declined to estimate how much the VCI system can boost a retailer's sales conversion rates.
The company isn't the only provider of big data analytics systems for physical stores. Silicon Valley startup RetailNext, for instance, uses an on-premise Linux server to collect and analyze data from a variety of in-store devices, including video cameras and point-of-sale systems.
Social media make the customer more powerful than ever. Here's how to listen and react. Also in the new, all-digital The Customer Really Comes First issue of The BrainYard: The right tools can help smooth over the rough edges in your social business architecture. (Free registration required.)