Prediction of wine quality using Multiclass Classification analysis
In this experiment we predict wine quality using Multiclass Classification analysis. The data contains quality ratings for a few thousands of wines (1599 red wine samples), along with their physical and chemical properties (11 predictors). We want to use these properties to predict a rating for a wine. Several classification algorithms will be applied on the data set and the performance of these algorithms will be compared. The original data had several labels with some of the labels having very few instances. Using Execute R Script module, I relabel the data as Low, Med and High, reducing it to a multi-class classification problem with three classes. I also use permutation feature importance module in the experiment to see which attributes have the highest predictive power. Published by a Microsoft employee.