Mackmyra has distilled whisky for 20 years in Sweden and to celebrate that, they wanted to deliver something extra special.
And they truly did. Intelligens has received numerous awards, ranging from American Distilling Institute's Gold Label and Best International Malt Whisky trophies to the world-renowned ADC Silver Cube in Product Design.
The starting point
Aqua vitae. Uisce beatha. Whisky.
Over 1,000 years ago, travelling monks migrated from mainland Europe to discover new worlds. Their paths led them to Scotland and Ireland, and among their collective wisdom, was the knowledge of distillation – the process of extracting and purifying liquid.
Lacking the vineyards and grapes from their original lands, they began to ferment grain mash – a mixture of water, grain and yeast – and in doing so, introduced the first whisky to the world.
Derived from the Gaelic word uisce, meaning water, distilled alcohol was known in Latin as aqua vitae, or water of life. This was translated into Old Irish as uisce beatha, before various iterations in early English gave us the whisky (or whiskey) we know today.
Since these early beginnings, whisky production has spread to all corners of the globe. From Ireland and Scotland, to Japan, the US, Australia and more, this ancient art has traversed cultures and boundaries, with each distillery infusing their unique soul into each blend.
Sweden-based Mackmyra Whisky is one such distillery. Founded in 1999 after eight friends decided to create their own whisky, it has since won several international awards, and its Master Blender has recently been inducted into Whisky Magazine’s hall of fame. The distillery’s ambitions, however, reach much further.
Together with Fourkind, part of Thoughtworks, Mackmyra created the world’s first whisky developed completely by machine learning. In an industry synonymous with deep-rooted tradition, human expertise and craftsmanship, what happens when 1,000-year-old techniques meet advanced 21st Century technology?
We always strive to challenge the traditions in the very traditional whisky trade and that’s something we really do now when we develop a whisky with the help of AI. 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. For me as a master blender, it is a great achievement to be able to say that i’m now also a mentor for the first ever created AI whisky in the world.
It's all in the blend
To better understand the role of machine learning as distiller, we first need to understand what gives whisky its distinct character. Whiskies aren’t just differentiated by their different ingredients, but also by the charred wooden casks they’re stored in. Rather than mere containers, the casks themselves play a vital role in giving each blend its unique flavor.
When whisky is first distilled, it’s a clear liquid that can have an elegant or a smoky character. To get the rich aroma, flavour and color we are used to seeing, this clear form, known as new make, needs to spend at least three years (usually much longer) in wooden casks. This is the maturation phase, where the all-important flavour infusion takes place.
Over time, whiskies slowly begin to take on the colour, aroma and flavours from the casks in which they’re stored, which also includes the flavours and aromas of their previous contents, such as bourbon, sherry, wine or other styles of spirit. “From these casks, we can generate hundreds of thousands of different whiskies,” states Angela D’Orazio, Master Blender of Mackmyra.
Master Distillers can spend their whole lives meticulously tasting, tweaking and experimenting to create the best flavours possible, turning acts of chemistry into a form of art – and this is where Mackmyra wanted machine learning to work its magic.
The process
Humans have always selected the different blends of ingredients and casks to create near-infinite flavor combinations. To do so, we first explored all current generative models but due to poor performance, ended up creating a proprietary generator-discriminator model that was designed to explore new spaces and generate unique recipes, but we also wanted to make the best possible whisky. We used previous recipe data, tasting notes, ratings of previous recipes, expert reviews, customer reviews and cask information – internal ratings, cask types, filling stages, volumes and alcohol levels to make our model understand what’s Mackmyra whisky. Then we created a framework which can innovate in this space, creating new whiskies that are unique but ultimately taste excellent.
This was not only faster than a person carrying out the process manually, but thanks to the algorithm’s ability to sift through and calculate a vast amount of data, new and innovative combinations that would otherwise never have been considered, could be found.
It’s important to stress, however, that this solution is not designed to replace a Master Blender. “The work of a Master Blender is not at risk,” Angela states. “While the whisky recipe is created by AI, we still benefit from a person’s expertise and knowledge. We believe that the whisky is AI-generated, but human-curated. Ultimately, the decision is made by a person.”
This methodology can have an impact in different industries globally. I envision machine learning systems generating recipes for sweets, perfumes, beverages and sneaker designs. Many of these have already been attempted, but large-scale adoption is still lagging behind. We are showing the way forward, and these new machine learning 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.
The Taste
Color: Golden yellow
Nose: Toffee & cream vanilla, fine oloroso tones and fruit with citrus, pear & apples. Herbal notes of aniseed, ginger and white pepper and a light tone of toasted oak casks.
Mouth: Vanilla with fine oak notes, fruits with citrus & pear, herbal spices with slight tobacco leaves and a very small hint of smoke.
Summary: Fruity and oaky, slightly salty and with a dryish end.
What does this mean for your organization?
With our approach we have gained the following benefits:
- Augmented innovation space for human innovators: ideas and combinations that wouldn’t been considered otherwise
- Faster and more cost-efficient innovation process: products don’t need to be manufactured and released for consumers to get feedback
- Better product-market fit due mathematical & evolving machine learning model at the core