A E-Business Case of Study: Modelling the Quality of the Wine using its Physicochemical and Qualitative Properties

The main purpose of this research was to find relations between the chemical composition of the wines and the wine testers' opinions on the wine quality. We used in our study a dataset which contains examples of red wine from Vinho Verde, Portugal. Firstly, we did an analysis on the attributes of the examples, in the dataset, to find correlations between quantitative and qualitative properties in wines. Secondly, we performed clustering using the algorithms k-means and x-means. Additionally, we used the J48 algorithm for getting a decision tree and then to extract first order logic rules. We concluded that, there is a relation between physicochemical properties and quality of wines. This result opens the possibility of further analysis and perhaps this could lead to use fewer wine testers and therefore, our research could bring benefit to the wine industry.