The use of decision support systems by the wine industry is mainly focused
on the wine production phase [10]. Despite the potential of DM techniques to
predict wine quality based on physicochemical data, their use is rather scarce
and mostly considers small datasets. For example, in 1991 the famous “Wine”
dataset was donated into the UCI repository [2]. The data contain 178 examples
with measurements of 13 chemical constituents (e.g. alcohol, Mg) and the goal
is to classify three cultivars from Italy. This dataset is very easy to discriminate
and has been mainly used as a benchmark for new DM classifiers. In 1997 [22],
a NN fed with 15 input variables (e.g. Zn and Mg levels) was used to predict six
geographic wine origins. The data included 170 samples from Germany and a
100% predictive rate was reported. In 2001 [24], NNs were used to classify three
sensory attributes (e.g. sweetness) of Californian wine, based on grape maturity
levels and chemical analysis (e.g. titrable acidity). Only 36 examples were used
and a 6% error was achieved. More recently, mineral characterization (e.g. Zn
and Mg) was used to discriminate 54 samples into two red wine classes [17]. A
probabilistic NN was adopted, attaining 95% accuracy. As a powerful learning
tool, SVM has outperformed NN in several applications, such as predicting meat
preferences [6]. Yet, in the field of wine quality only one application has been
reported, where spectral measurements from 147 bottles were successfully used
to predict 3 categories of rice wine age