Predicting Wine Score based on Physicochemical Properties
DOI: 10.23977/afshn.2022.040101 | Downloads: 32 | Views: 1478
Author(s)
Congrui Li 1
Affiliation(s)
1 School of Statistics, Beijing Normal University, Beijing, 100875, China
Corresponding Author
Congrui LiABSTRACT
Existing wine scoring systems are based on subjective feelings, which are difficult to quantify. Thus, the score of a particular wine has little guidance on the brewing process. In this paper, regression tree and random forest are used to predict wine score by using the physicochemical properties of wine. According to the results of the model, higher quality wine can be produced by controlling the physical and chemical properties, thus reducing the waste of raw materials.
KEYWORDS
Random Forest, Regression Tree, Wine Score, physicochemical propertiesCITE THIS PAPER
Congrui Li, Predicting Wine Score based on Physicochemical Properties. Advances in Food Science and Human Nutrition (2022) Vol. 4: 1-5. DOI: http://dx.doi.org/10.23977/afshn.2022.040101.
REFERENCES
[1] Dua, D. and Graff, C. (2019). UCI Machine Learning Repository [http://archive.ics.uci.edu/ml]. Irvine, CA: University of California, School of Information and Computer Science.
[2]P. Cortez, A. Cerdeira, F. Almeida, T. Matos and J. Reis. Modeling wine preferences by data mining from physicochemical properties. In Decision Support Systems, Elsevier, 47(4):547-553, 2009.
[3] https://www.wine-world.com/culture/pj/20150605173918670
Downloads: | 1011 |
---|---|
Visits: | 28079 |