Airlines are conscious of how crucial customer happiness is to their bottom line. By prioritizing the needs of their customers, attending to their concerns, and consistently offering great service, airlines can build a loyal customer base, enhance their brand reputation, and maintain a competitive edge in the market. The goal of this research is to classify passenger satisfaction and dissatisfaction based on various features using a variety of machine learning techniques, including random forest, decision tree, K-nearest neighbours (KNN), Nave Bayes, ensembling techniques like XGBoost, AdaBoost, extra tree classifier, bagging classifier, and simple neural network. Finally, evaluate each model using metrics such as accuracy, precision, recall, F1-Score, and AUC-ROC Curves.