Skip to Content

Tracking a Shopper’s Habits

Infosys’s sensor network turns stores into mini-Internets.

Infosys may have solved a $100 billion problem for companies in the retail business: how to tell whether their promotions really work. In the process, Infosys has also created the potential for stores and consumer-goods companies to track things like traffic and inventory in real time.

Consumers like Procter & Gamble and the retailers they sell through spend more than $100 billion per year to promote products in stores, according to Forrester Research. They pay fees for shelf space in stores, including premiums to have their products at eye level. They pay for special promotion stands. And although they pay for armies of checkers to see whether retailers follow through on the deals, it’s a system fraught with error, says Forrester analyst George Lawrie.

“Stores make lots and lots of mistakes,” Lawrie says, noting that at many retail stores, the people who stock the shelves may have little or no interaction with the people who make the promotional deals. “In the big brands, the CFOs know they’ve had to hand these funds over to be eye level on aisle number one, and they don’t know if it’s really happening, and they’re beginning to start to ask if the stores can prove it.”

So Infosys, which counts 12 of the world’s 20 largest retailers among its current customers, has developed ShoppingTrip 360, a hosted software application that can track shoppers and inventory, using wireless sensors placed on shelving, promotional displays, and shopping carts. The sensors, which use the 802.15.4 wireless protocol to connect to each other in a mesh network, can send information such as where shoppers stop in a store, what products they pick up, what they put back, what they put in their cart, and whether a product is out of stock. Infosys has also developed an application to let consumers in the store use their cell phones to get information such as store maps, or to access an online shopping list or collection of recipes.

“This, we believe, is the next wave of innovation in the retail space,” says Infosys cofounder and CEO S. “Kris” Gopalakrishnan. He notes the push by retailers in the 1970s and ’80s to develop electronic data interchange, as well as the 1990s push into e-commerce. He says that Infosys is trying to usher in the in-store Internet.

Retailers and consumer-goods makers typically get data on a daily basis, from point-of-sale scanners. Getting better data about product sales was a big reason why retailers like Wal-Mart and Target pushed radio frequency identification (RFID) technology, minuscule radio chips that were expected to replace the bar code on individual products. But RFID chips remain too costly to be ubiquitous, and Lawrie says that they may never be. He says that the cost of the chips, coupled with the substantial amount that retailers would have to spend to outfit their stores to work with the chips, have limited interest in RFID.

What’s more, RFID raises privacy concerns that ShoppingTrip 360 might not. Infosys says that its system is completely anonymous, unless the consumer agrees via cell phone to tell the system who he or she is (and consumers can opt to identify themselves based on just their shopping-cart number). Infosys says that it will pay to install the sensors in stores, charging retailers only for the data that they want to use.

“I’m charging to tell them when stocks are reduced by a certain percentage, or when a consumer redeems a coupon through their mobile phone,” says Sandeep Dadlani, global head of sales for Infosys’s retail unit.

Exactly what the data will cost is not yet determined, says Gopalakrishnan. He says that Infosys is piloting the system at a number of large retailers in the United States, Europe, and Asia. Girish Ramachandra, head of the innovations practice for the Infosys retail unit, says that it is no harder to install its wireless sensors than to set up a wireless router in a home. Initially, it will take a week per store to deploy and test the system.

Infosys says that it is ready to offer three things: “heat maps” of stores that show levels of inventory, levels of inventory at the fronts of shelves, and concentrations of shoppers in the store; a smart shelf pad with a built-in wireless sensor that is powered by the store’s lights; and a shop-by-cell phone option, which lets consumers get recommendations or coupons on their phones.

Infosys thinks that there will be many other applications it can develop for the system, such as a “perpetual checkout” service that would let shoppers ring up their goods as they put them in their carts, allowing them to walk out of the store when they are finished shopping. For apparel retailers, the company is developing smart mirrors that will recommend combinations of clothing and automatically notify salespeople to bring things for shoppers to try on. Infosys could develop an application to let stores employ the sensor networks to manage energy usage. And it intends to open its development platform so that other companies can create applications for the service as well.

Forrester’s Lawrie says that without seeing the system in action in a store, it’s too early to say how well it will work. But if the system works as promised, he says, “this would be a huge breakthrough.”

Keep Reading

Most Popular

Large language models can do jaw-dropping things. But nobody knows exactly why.

And that's a problem. Figuring it out is one of the biggest scientific puzzles of our time and a crucial step towards controlling more powerful future models.

OpenAI teases an amazing new generative video model called Sora

The firm is sharing Sora with a small group of safety testers but the rest of us will have to wait to learn more.

Google’s Gemini is now in everything. Here’s how you can try it out.

Gmail, Docs, and more will now come with Gemini baked in. But Europeans will have to wait before they can download the app.

This baby with a head camera helped teach an AI how kids learn language

A neural network trained on the experiences of a single young child managed to learn one of the core components of language: how to match words to the objects they represent.

Stay connected

Illustration by Rose Wong

Get the latest updates from
MIT Technology Review

Discover special offers, top stories, upcoming events, and more.

Thank you for submitting your email!

Explore more newsletters

It looks like something went wrong.

We’re having trouble saving your preferences. Try refreshing this page and updating them one more time. If you continue to get this message, reach out to us at customer-service@technologyreview.com with a list of newsletters you’d like to receive.