Wine Quality Prediction Using Machine Learning Techniques

As wine tops as one of the most consumed beverages in the world, there have been several studies on improving wine quality over the years. Our paper aims to enhance the predictive accuracy of wine quality certification by leveraging the UCI Red Wine Quality dataset and various machine learning models: Support Vector Classifier, Random Forest, Decision Tree Classifier, and K-Nearest Neighbors (KNN). Through meticulous feature selection, key attributes affecting wine quality were identified. Our analysis revealed significant performance metrics across the models, highlighting the potential of machine learning in optimizing wine quality assessments. This data-driven approach underscores its efficacy in enhancing the precision and reliability of wine quality predictions.