Modern computational techniques offer new perspectives for the personalisation of food properties through the optimisation of their production process. This paper addresses the personalisation of beer properties in the specific case of craft beers where the production process is more flexible. Furthermore, this work presents a solution discovery method
that could be suitable for more complex, industrial setups. An evolutionary computation technique was used to map brewers’ desired organoleptic properties to their constrained ingredients to design novel recipes tailored for specific brews. While there exist several mathematical tools, using the original mathematical and chemistry formulas, or machine learning models that deal with the process of determining beer properties based on the predetermined quantities of ingredients, this work investigates an automated quantitative ingredient-selection
approach. The process, which was applied to this problem for the first time, was investigated in a number of simulations by “cloning” several commercial brands with diverse properties. Additional experiments were conducted, demonstrating the system’s ability to deal with on-the-fly changes to users’ preferences during the optimisation process. The results of the experiments pave the way for the discovery of new recipes under varying preferences, therefore facilitating the personalisation and alternative high-fidelity reproduction of existing and new products.
This is an open access article distributed under the Creative Commons Attribution License
which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.