Clustering and Classification of Red Wines According to Physical-Chemical Properties Using Data Mining Methods

The data on 178 samples of Italian red wines taken from the public machine learning repository UCI have been studied. Computer analysis of 13 physico-chemical properties of the wine samples on their distribution between three groups has been performed via different data mining methods. Classification models: factor, discriminant, canonical, and neural network (multilayer perceptron MLP, Kohonen's map SOFM) ones, predicting models (support vector machine, Bayesian classifier, and nearest neighbor method), and decision trees have been built. The neural network classifiers SOFM 13-3, MLP 13-5-3, and SOFM 16-3 have been trained. It has been found that predicting power of the models is determined by the following variables: proline, flavonoids, color intensity, proteins, and alcohol.