A machine learning application in wine quality prediction

The wine business relies heavily on quality certification. excellence of New Zealand Pinot noir wines is well-known worldwide. Our major goal in this research to predict by generating synthetic data and construct a machine learning model based available experimental collected from different diverse regions across Zealand. We utilised 18 samples with 54 characteristics (7 physiochemical 47 chemical features). generated 1381 12 original using the SMOTE method, six were preserved for testing. findings compared four distinct feature selection approaches. Important attributes (referred as essential variables) that shown be relevant at least three methods quality. Seven algorithms trained tested holdout sample. Adaptive Boosting (AdaBoost) classifier showed 100% accuracy when evaluated without selection, (XGB), variables (features found important methods). In presence variables, Random Forest (RF) performance was increased.