Please use this identifier to cite or link to this item:
Title: Selection of features and prediction of wine quality using artificial neural networks
Authors: Athanasiadis, Ioannis
Ioannides, Dimitrios
Type: Article
Subjects: FRASCATI::Natural sciences::Mathematics::Statistics and probability
Keywords: Linear regression
neural networks
physicochemical properties
statistical methods
Issue Date: 2021
Source: Electronic Journal of Applied Statistical Analysis
Volume: 14
Issue: 2
First Page: 389
Last Page: 416
Abstract: The assessment of wine taste quality is a key factor for successful sales in the wine industry, where the aim is to fulfill the consumer's needs. Usually, this is determined by human experts who make the evaluation process very expensive and time-consuming. This study intends to introduce an alternative method for the prediction of wine quality with the usage of machine learning techniques such as linear regression and neural networks. Our data analysis is based on a real wine dataset provided by an established winery in Greece. First of all, we determine the dependence of the quality from selected physicochemical features of wine. We use some well-known algorithms to achieve better results in statistical calculations and specific methods of selecting the best possible number of variables using principal component analysis (PCA) and linear regression. After using artificial neural networks and checking various combinations of layers we conclude how the proposed statistical techniques improve the accuracy of the prediction of the wine quality using the previously selected features.
ISBN: 2070-5948
Other Identifiers: 10.1285/i20705948v14n2p389
Appears in Collections:Department of Economics

Files in This Item:
File Description SizeFormat 
22657-137161-2-PB_final_version.pdfSelection of features and prediction of wine quality using artificial neural networks696,52 kBAdobe PDFView/Open

This item is licensed under a Creative Commons License Creative Commons