A Pugnacious Comparative Study of Data Analysis Techniques for Wine Quality Prediction

The wine industry has experienced exponential growth over the past few decades, with a corresponding surge in consumption. This growth has necessitated an increased emphasis on quality. To achieve this objective, data analysis and machine learning techniques can be employed to build robust models. Understanding how the variation in one or more of the physicochemical factors associated with the wine affects the overall quality of the wine and recognizing the factors that contribute the most to determining this quality using feature selection are the primary objectives of this study. A comparison of various techniques used for achieving the same has been presented.