• T M Geethanjali
• Sowjanya M Y
• Rohith S N
• Shubhashree B E
• ShourishCharan A

Wine classification is a difficult task and also we do not know on what basis taste can be identified and considered to be a good wine. Predicting the quality of wine can help in certification phase, at present sensory analysis is performed by food tasters being clearly a subjective approach. Furthermore, a feature selection process can help to analyze the impact of the analytical tests. For our work, we collected the dataset of various red and white variants of the Portuguese "Vinho Verde" wine from Kaggle, this includes various physicochemical properties. We used Google Colab to work on this dataset. Machine learning algorithms are used to detect few excellent or poor wine qualities. We preprocessed the data by identifying and handling the missing values. One Hot encoder is used to convert the categorical values into numerical values. The Feature Scaling step is used to normalize the range of independent variables. We have many machine learning algorithms for prediction among them we used Logistic Regression, Decision Tree Classifier, Random Forest Classifier and Extra Trees Classifier. We trained the dataset by all the four models and compared the accuracy and precision to choose the best machine learning algorithm. In turn, this helps us to predict the quality of wine on a range of 0–10 given a set of features.

Wine Quality, Machine Learning, Logistic Regression, Random Forest Classifier, Decision Tree, Extra Trees Classifier.

"Prediction Of Wine Quality Using Machine Learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.8, Issue 11, page no.d175-d182, November-2021, Available :http://www.jetir.org/papers/JETIR2111328.pdf

"Prediction Of Wine Quality Using Machine Learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.8, Issue 11, page no. ppd175-d182, November-2021, Available at : http://www.jetir.org/papers/JETIR2111328.pdf