Australia’s largest locally-owned ale maker, Coopers Brewery, has turned to big data analytics to perfect and protect its flagship pale ale in the face of seasonal variations in its ingredients.
An eight-week project was led by the Data to Decisions Cooperative Research Centre (D2D CRC), supported by the federal and South Australian governments, in a bid to quantify and quantify the impact ingredients of different quality would have on the beer.
“The bottom line is, we need to understand, manage and control the inputs and processes so as to ensure not just the quality of the product, but that it is always the same, day-in-day-out, year-in-year-out,” Coopers supply chain manager Dr Jon Meneses said.
“The challenge for all manufacturers is how to do this when there will always be ingredient seasonality and variations to the brewing process.
“Our team came up with the top 10 parameters which can positively and negatively affect the quality of our beer. Getting the data is easy, turning it into knowledge and deliverables is the big challenge,” Meneses added.
D2D lead data scientist Dennis Horton said that the complexity of the brewing process increases the difficulty of ascribing subtle variations in the final product to different aspects of the raw ingredients.
“We spent eight weeks developing an algorithm to perfect the brewing process and ensure a quality final product, including firmer foam that lingers longer,” Horton said.
That involved linking and analysing data from all of the stages of the brewing process to better understand the development of the pale ale.
“The algorithm identified the top ten most important components out of the hundreds of possible brew settings and ingredients,” Horton said.
“These results provide valuable insights into the brewing process and can help Coopers manage the quality of the final product despite the complex nature of brew settings and ingredients.
“The results both confirmed their previous ideas of the important components as well as revealed other factors that impact on final quality.”
While Coopers is yet to permanently adopt the algorithm into its wider brewing practices, the company is interested in exploring what else data analytics can do for beer.
“While we have a great product, we are always looking for ways to improve and do things better,” Meneses said.