Mars Wrigley UK has teamed with Google in the name of better baking.
The two companies partnered to develop the Maltesers AI Cake, which leverages artificial intelligence and machine learning to craft a hybrid cookie/cake dessert.
It’s the first time Mars Wrigley has used AI in this manner, a spokesperson confirmed to CGT.
A machine learning model developed by Google Cloud employs hundreds of recipes to create the Maltesers AI cakes. They’re frosted with Marmite-infused buttercream, chosen as a result of Google Search Trends identifying “Is Marmite sweet or savory” as a top search around “sweet and salty.”
“This idea opened our eyes to the endless possibilities of how AI can bring innovation to the kitchen by creating a foundation for recipe development,” said Sam Chang, global head of data science and advanced analytics at Mars.
Christine Cruz-Clarke, Mars Wrigley UK marketing director, added the collaboration with the Google Cloud AI team enabled it to find new avenues to inspire “more better moments at home.”
For her part, Cathryn Sleight, chief growth officer at Mars Wrigley, described it as "the sensorial equivalent of Miley Cyrus’s ‘Wrecking Ball.'"
The ML model was created by Sara Robinson, senior developer advocate at Google Cloud, who noted a striking difference about this particular model: “Unlike most ML models, this one required testing in the kitchen to make sure the ingredient combinations generated by the model produced baked goods you’d actually want to eat. Picture me and my laptop in a cloud of flour, tasting batter and frosting, and eating way too many Maltesers along the way.”
The company is promoting the innovation through a #BakeAgainstTheMachine bake-off with Peter Sawkins, winner of the 2020 Great British Bake Off Winner. Sawkins created his own competing Meltesers dessert, and consumers can visit Bakeagainstthemachine.co.uk to cast their vote in the challenge.