There’s more than ice cream in 100,000 of our freezer cabinets. Find out how we’re equipping them with image capture and AI tech to track stock levels in real time, provide data insights to our sales teams and help our retailers maximise revenues.

Globally 100,000 of our ice cream freezer cabinets have AI, and our goal is for 350,000 by the end of 2025
Image tech and AI capture stock levels to ensure retailers always have bestsellers in the freezer
Data insights from our AI freezers have increased retail orders and sales by up to 30%
Ice cream is the ultimate on-the-go treat. With a fleet of 3 million ice cream freezer cabinets strategically placed in shops, airports and supermarkets around the world, Unilever is leveraging technology like AI to meet consumer demand effectively.

“To win those impulse sales, our brands need to be available at the right place and the right time,” says Sarosh Hussain, Ice Cream’s Head of Digital Selling Systems.

“For example, if a customer breaks their journey at a petrol station to buy a Magnum and the freezer is out of stock, there’s no second chance, the sale’s lost.”

Rolling out AI across our freezer fleet
Most of our ice cream brands are sold via distributors who have significant numbers of retailers to serve.

Ensuring the retailers who host these freezers always have our bestsellers in stock was a key driver in equipping ice cream cabinets with AI.

Work is currently under way to add the tech to 30% of our top-selling ice cream cabinets for priority markets. To date, 100,000 freezers have been fitted with the technology. “We’re aiming to reach 350,000 in the next two years,” says Sarosh.

Smart freezer restocking
The software in each freezer unit is carefully positioned to only take photos of the stock inside the freezer, rather than general images of the shop.

The images are taken periodically and automatically sent to the cloud where they’re analysed by AI that’s trained to only identify our ice cream brands, analyse their depth in cabinet and use an algorithm to generate an order for the distributor.

“It’s like two eyes are looking at our stock every day,” Sarosh says. It also means whenever a retail outlet asks for stock, the distributor knows from the data exactly what their freezer needs.

Winning sales with actionable data
So far, the uptick in retail orders and sales thanks to data from our AI enabled freezers has been significant.

“There is no one size fits all. It varies from country to country,” says Sarosh. “But we have seen incremental growth that ranges from 8% in Turkey to 12% in the US and up to 30% in Denmark.”

In Hungary where almost 10% of its freezer fleet has been AI-enabled this summer, work has also been done to integrate the freezer’s system with those used by distributors.

As well as seeing the retailer’s regular ice cream order, distributors receive an order recommendation based on images and AI analysis of the stock levels in the cabinet.

The response from both distributors and retailers to these ‘recommendations’ has been positive. So far, close to 5% of orders have been generated from the AI system’s input this ice cream season.

Upskilling sales teams and driving cost-efficiencies
“The data is also helping upskill our sales teams by providing them with insights that allow them to get to know their businesses better to cross or upsell and make their calls more productive and proactive.

“Knowing what stock needs to be replenished before going into an outlet means the time usually taken up by the order process can be used on tasks like new business development and merchandising,” Sarosh adds.

And these aren’t the only benefits. Every ice cream order is fulfilled by refrigerated vans. “If you have a more accurate understanding of which customer wants what, distributors can plan their tertiary route and distribute to the outlets efficiently and more cost-effectively,” he says.

To win impulse sales, our brands need to be available at the right place and the right time.

Sarosh Hussain, Ice Cream’s Head of Digital Selling Systems
Aligning data with our marketing
Big data from our freezer fleet will also give us clearer insights into the performance of new product launches as well as marketing campaigns.

“By analysing this data, we should be able to understand if our ice cream brand’s above-the-line campaigns have had a positive correlation on freezer sales and stock.

“We’ll be able to compare freezer sales from previous seasons to determine if new products are adding value or cannibalising our core, and have the insights to reassess promotion planning and reforecast accordingly,” Sarosh says.

Big data, big opportunities for the future
Ensuring availability and share of shelf is just the start of what our AI-enabled freezers can do.

“If 350,000 of our freezer fleet are AI-enabled, we’ll have a large enough data set to provide analytics on product visibility and supply chain strategy. And we’ll be able to grow our ice cream sales by serving our shoppers better than ever before.”