WINE QUALITY PREDICTION SYSTEM USING SUPERVISED & UNSUPERVISED MACHINE LEARNING TECHNIQUES

Abstract

Wine quality prediction is a critical task in the wine industry, enabling producers to optimize the quality of their products. This project aims to develop a model for predicting the quality of wine using both supervised and unsupervised machine learning techniques. The system will leverage various physicochemical properties of wine, such as acidity, alcohol content, sugar levels, and pH, to predict the wine's quality based on a given scale. Supervised learning algorithms like regression models and classification models will be used to predict the quality score, while unsupervised techniques like clustering will help group wines with similar characteristics, aiding in segmentation for better quality prediction. The goal is to develop a robust model that can accurately predict wine quality and provide actionable insights for improving production processes.