Wine quality and type prediction from physicochemical properties using neural networks for machine learning: a free software for winemakers and customers.

Mor, Nuriel Shalom; Asras, Tigabo; Gal, Eli; Demasia, Tesfahon; Tarab, Ezra; Ezekiel, Nathaniel; Nikapros, Osher; Semimufar, Oshri; Gladky, Eva; Karpenko, Maria; Sason, Daniel; Маслов, Д. Н.; Mor, Omri

doi:10.31220/agrirxiv.2022.00125

Cited by 3 publications

(1 citation statement)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These revolutionary approaches are used to extract valuable insights from huge collections of data. Within this domain of wine evaluation, machine learning serves as a tool to be turned into a valuable outcome by processing big data to signi cant and valuable insights (Mor et al, 2022). By means of employing the patterns that prevailed before with a good level of accuracy, machine learning models make the prediction of results that is predictable to a high level of accuracy.…”

Section: Introductionmentioning

confidence: 99%

Machine Learning-Based Wine Quality Prediction Using Python: A Predictive Modeling Approach

Singh,

Quraishi,

Ather

et al. 2024

Preprint

View full text Add to dashboard Cite

Focusing on the fact that there are deep intricacies involved in a wine's quality and the possibility of having predictive analytics, the current study reviews the effectiveness of various machine learning models at predicting the quality of red wines. Using a wine dataset that includes pleasure of taste, sugar content, average total alcohol, and different parameters, we optimize the data through the use of preprocessing techniques including feature selection and normalization. The choice of a Random Forest Classifier, deemed recognizable for its efficiency and accuracy when dealing with the complexity and multidimensionality of the data, is one of the key components of the methodology we propose. Our study elicits a considerable concern for sciences and future prediction, offering very keen answers as to the primary factors that drive the ranks of wine. Through this study not only the role of machine learning is being enriched, but also the fundamental basis for the foreseeing of beverage quality appears to be established which can be used as a model for the following research work. Thereby, this research work would have a multiplex of impacts on the fields of enology and computational analytics by offering an example for the implementation of the modern machine learning algorithms with the existing approaches to the evaluation of the wine quality. JEL Code: Y90

show abstract

Section: Introductionmentioning

confidence: 99%

Machine Learning-Based Wine Quality Prediction Using Python: A Predictive Modeling Approach

Singh,

Quraishi,

Ather

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

Clustering of Organoleptic Quality Evaluations of Red and White Wines by Physicochemical Parameters Using STATISTICA Software

Bondarev

2023

Russ J Gen Chem

View full text Add to dashboard Cite

Clustering of organoleptic quality evaluations of red and white wines by physicochemical parameters using statistica software

Bondarev

2023

Žurnal obŝej himii

View full text Add to dashboard Cite

Organoleptic evaluations in a ten-point scale of wine experts and experimental physicochemical parameters of red (1599 samples) and white (4898 samples) wines of Portuguese manufacturers were analyzed using STATIS-TICA sofware. Methods of agglomerative and iterative ( k -means algorithm) clustering revealed the grouping of similar wine samples into three, four and six clusters depending on the Euclidean distance of association. The quantitative filling of clusters with samples of bad wines (grades 3 and 4), normal wines (grades 5 and 6) and good wines (grades 7, 8, 9) was established. Neural network (MLP) and discriminant analyzes (DA) were performed; algorithms of classification trees (CT), support vector machines (SVM), naive Bayesian classification (NBC) and nearest neighbors (kNN) were involved. The best performance was demonstrated by neural network models. Multilayer perceptorons classifiers were trained: for red wines - MLP 11-7-3, MLP 11-13-4, MLP 11-14-6; for white wines - MLP 11-9-3, MLP 11-5-4, MLP 11-9-6. The properties of wines, whose contribution to the separating power of classifiers is decisive, are revealed. The ranges of changes in physicochemical parameters in three clusters of red and white wines for bad, normal and good wines were given.

show abstract

Wine quality and type prediction from physicochemical properties using neural networks for machine learning: a free software for winemakers and customers.

Cited by 3 publications

References 13 publications

Machine Learning-Based Wine Quality Prediction Using Python: A Predictive Modeling Approach

Machine Learning-Based Wine Quality Prediction Using Python: A Predictive Modeling Approach

Clustering of Organoleptic Quality Evaluations of Red and White Wines by Physicochemical Parameters Using STATISTICA Software

Clustering of organoleptic quality evaluations of red and white wines by physicochemical parameters using statistica software

Contact Info

Product

Resources

About