Enhancing Wine Quality Prediction Through Machine Learning Techniques

Wine is Popular across the globe, enjoyed by all genders. As wine ages, its taste improves, though it becomes more expensive. Previously, human experts exclusively evaluated wine quality, but now software-based systems assist in these tasks, reducing time and effort while maintaining Precision. Traditional Approach for predicting wine quality takes more time and lack of consistency for accurate production. Today, Machine Learning algorithms provide a more reliable approach, utilizing automatic predictive systems within decision support platforms. This study is about predicting whether wine quality is Good or Bad based on their physio chemical properties using various machine learning techniques like gradient boosting regressor, support vector classifier, s tochastic g radient decent model, logistic regression, neural networks, knn,random forest on dataset "Vinho Verde" Wine dataset from Portuguese. The final r esults a re c ontrasted w ith a ctual v alues. A fter comparing with actual values Random Forest technique scored high accuracy in white wine dataset as well as in red wine dataset compared with other techniques used with 94.68% and 88.57% accuracy. This Work will be highly beneficial in wine industries to predict the correct quality of a specific wine with less effort and time.