For passengers traveling on roadways, airways, and waterways, survival chances must be predicted to prevent the loss of human life and property damage, including buses, airplanes, and ships. In this paper, a dataset that contains passenger information has been taken. Many algorithms are applied to predict the passenger survival chances (Logistic regression model, SVM model, KNN model, Gaussian Naive Bayes model, decision tree model). The results show that the Naive Bayes model is getting the maximum accuracy score in predicting the survival chances of passengers. Several machine learning models were used to measure the accuracy of predicting passenger safety using the proposed methodology. Some of the models that have been studied include K-nearest neighbours (KNN), Decision Trees, Naive Bayes, Logistic Regression, and Support Vector Machines (SVM). The most effective methods were logistic regression (75.74%), decision trees (74.25%), KNN (66.04%), and SVM (63.8%), in that order, following the Naive Bayes algorithm, which achieved the highest degree of success with an accuracy score of 76.86%.