Is there a magic formula for brewing the perfect beer? If there is, then given the drink’s timeless popularity, whoever finds it is likely to be very successful. It’s a question that the world’s largest brewer is hoping to answer with the help of artificial intelligence (AI).
AB InBev – producer of renowned brews including Budweiser, Stella Artois, and Corona - is building machine learning into key areas of its business, as it seeks to bring one of the world’s oldest industries into the digital age.
The company has invested in a raft of data-driven initiatives with the aim of improving everything from how it brews beer to how it manages its relationships with customers and markets its products to the public.
It began its steps towards digital transformation several years ago by establishing what it refers to as its Beer Garage – a Silicon Valley-based hub of innovation, where it researches, develops, and tests technology-driven solutions.
AB InBev’s global director of innovation, Andrew Green, spoke to me about the challenges involved with adding cutting-edge technology to the brew.
He tells me “The Beer Garage is our emerging technology office in Silicon Valley – as a company we’re super-committed to innovation, so placing people out here to be really in the forefront of what’s happening is very exciting for us.
“It’s like we’re opening doors to the external ecosystem and inviting them in to collaborate and co-create with us.”
A key component of their Silicon Valley operations is the technology incubator, which is where several of the AI-powered initiatives currently being trialed or rolled out into production originated. But proximity to the larger tech companies of Mountain View, as well as being able to tap into the networks of the venture capitalists in the area, are all sources of opportunity and innovation.
Green explains, "We spend most of our time working with startups – early-stage companies as well as larger startups, and we learn a lot from working with them … it's a really exciting way of working for us … these early-stage founders are super motivated and experts in their field, which is inspiring for us."
The Beer Garage’s function is to sit between this startup ecosystem and the core AB InBev business, and discover ways that each can be of benefit to the other. These will generally be new concepts that can be quickly scaled up to the point where they can operate within one of its multinational operations.
How is AB InBev using AI right now?
Green talked me through three use cases across very different areas of the company’s business. The first is a system called SenseAI that uses machine learning to help brewers improve the quality and flavor of their products.
It involves using real-time analytics to measure data collected during the brewing process – from levels of CO2 used in the processes to the time dedicated to each different stage – to predict qualities of the end product.
Green says, "Supplying breweries is a big thing for us … so SenseAI was setting out to say, 'we have all of this data, how can we utilize it to put the best product we possibly can into our consumers' hands?"
Other data that is used includes results gathered from a grading process, where expert human beer tasters assess the taste of the algorithmically-informed brew.
At the moment this layer of human input is essential – no digital “tasting” system has yet been developed that is able to give as comprehensive and reliable assessment of the taste and quality of a finished beer, as an expert with a biological tongue and brain. But, “In the future, its totally possible we can put a more objective spin to that, as some of these things become more possible to do in a scalable way through technology,” Green says.
