Abstract: Wine production is the result of the interaction between various strains and grapes, and its good quality is also affected by many factors. Aureobasidium, Cladosporium, Candida, Filobasidium, Hanseniaspora, Hannaella, Saccharomyces, Wickerhamomyce, Alternaria, Starmerella, Acetobacter, Papiliotrema, Bradyrhizobium, Leuconostoclia, Gluconobacter, Comamonas, and Massilia, are significantly correlated with changes of physiological properties and volatile compounds. Phenolic compounds, shortened as phenolics, are a vital parameter to the quality of wine, and wine phenolics include two main families: non-flavonoids, which consist of hydroxybenzoic acids (HBAs), hydroxycinnamic acids (HCAs), and stilbenes, and flavonoids, comprising flavonols, flavan-3-ols, and anthocyanins. Wine quality is determined by either sensory tests or physicochemical tests, and the latter analyse the wine’s chemical parameters such as sugar, pH, and alcohol level. The most important constituents found in wine are Terpenes; Aldehydes, Pyrazines, Esters, Ketones and diketones, Mercaptans, and Lactones. In wine quality analysis, the most chief variables are volatile acidity, alcohol, sulphates, citric acid, density, total sulfur dioxide, chlorides, pH, fixed acidity, free sulfur dioxide, and residual sugar. Some classifiers utilized for wine quality prediction in machine learning are: k-Nearest Neighbor (KNN), Random Forest, Decision Tree, Support Vector Machines, Linear Regression, Stochastic Gradient Descent, Artificial Neural Networks (ANN), and Naive Bayes. This article is aimed to review wine quality parameters, detection and traceability of wine, and detection of harmful substances in alcohol and liquor composition analysis.