The wine quality is important for the consumers as well as for the wine industry. The traditional (expert wine tester) way of measuring wine quality might be expensive and time-consuming. Nowadays, machine learning models are foremost tools to replace human intervention. As a sub field of Artificial Intelligence (AI), Machine Learning (ML) aims to understand the structure of the data and fit it into models, which later can be used on unseen data to achieve the desired task. Machine Learning has been widely used in various sectors such as Businesses, Medical, and Astrophysics to name a few and many other scientific problems. Inspired by success of Artificial Intelligence in various different sectors here, we can use it for wine quality prediction based on various physicochemical properties of wine. Among various machine learning methods, we analyze the performance of Extremely randomized trees (Extra trees), Extreme Gradient Boosting (XG Boost) and Light gradient-boosting machine (Light GBM) ensemble ML methods. This work demonstrates how statistical data analysis can be used to identify the components that mainly control the wine quality prior to the production.
