Prev
Title: Modeling wine preferences by data mining from physicochemical properties
Background:
Vinho Verde is a Portuguese wine from the Minho region in the far north of the country. The name literally means "Green Wine" (red or white), referring to its youthful freshness that leads to a very slight green color on the edges of the wine. ...
Prize:
US $500
Contest and Data:
The two datasets are related to red and white variants of the Portuguese "Vinho Verde" wine. Only physicochemical (inputs) and sensory (the output) variables are available (e.g. there is no data about grape types, wine brand, wine selling price, etc.). These datasets can be viewed as classification or regression tasks. The classes are ordered and not balanced (e.g. there are much more normal wines than excellent or poor ones). Outlier detection algorithms could be used to detect the few excellent or poor wines. Also, we are not sure if all input variables are relevant. So it could be interesting to test feature selection methods. The goal of the competition is to develop a predictive algorithm that can identify the overall quality of the wine based on the following input variables:
1 - type (red or white)
2 - fixed acidity
3 - volatile acidity
4 - citric acid
5 - residual sugar
6 - chlorides
7 - free sulfur dioxide
8 - total sulfur dioxide
9 - density
10 - pH
11 - sulphates
12 - alcohol content
Output variable (based on sensory data): 13 - quality (score between 0 and 10)