Mackmyra will use AI to combine existing recipes, customer preferences and sales data
Elly Yates-Roberts |
Sweden-based whisky distillery Mackmyra is using artificial intelligence (AI) to create new flavour combinations. According to a Microsoft article, the tech from Microsoft and Finnish firm Fourkind, will use existing recipes, customer preferences and sales data to suggest innovative tipples.
When first distilled, whiskies are clear. To take on the rich qualities and colour we associate with the spirit, it must be matured in wooden casks for at least three years. It is this process that gives whiskies their different flavours, infusing with the aromas of whatever used to be stored in the cask.
Traditionally it is the job of master distillers to individually taste and experiment with these flavours to give each drink its signature – but Mackmyra is speeding up this process up with AI.
“We always strive to challenge the traditions in the very traditional whisky trade, and that’s something we can really do now with the help of AI,” said Angela D’Orazio, master blender at Mackmyra. “We see AI as a part of our digital development and it is really exciting to let AI be a complement to the craft of producing a high-quality whisky.”
The distillery’s machine learning models are powered by Microsoft Azure and use the various data to predict popular, high-quality flavours based on the available casks. This not only speeds up the process but also finds combinations that a human could not.
“The work of a master blender is not at risk,” said D’Orazio. “While the whisky recipe is created by AI, we still benefit from a person’s expertise and knowledge, especially the human sensory part, that can never be replaced by any program. We believe that the whisky is AI-generated, but human-curated.”
The AI-generated whisky will be available from Autumn 2019 and according to the distillery, it is the first complex consumer product recipe to be created with machine learning.
“This AI-generation can have an impact in different industries globally,” says Jarno Kartela, machine learning partner at Fourkind, the company behind the AI algorithm. “I envision AI systems generating recipes for sweets, perfumes, beverages, and maybe even sneaker designs.
“We are showing the way forward and these new AI solutions can be used to generate products that retain the spirit, look and feel of the brands behind them, while at the same time being new and unique.”