Various machine learning models are used with the Titanic data to predict any survival rate getting an in-depth analysis during this study. This paper analyzes the performance of Decision Trees, Random Forests, Support Vector Machines (SVM), and Neural Networks, including the data preprocessing steps of feature engineering and hyperparameter optimization. Precision, accuracy, recall, F1-score, and AUC are used to measure the models based on their overall performance properties. Neural Network and SVM had the same 82 percent accuracy with the best recall of 73 percent on the survivor category; hence, the most suitable in recognizing the survivors. Random Forest scored with 82 percent precision rate but as a whole, it scored less than Decision Tree, which scored 78 percent. The contribution of this work is that it gives a comparative analysis of four widely-used machine learning techniques on the Titanic dataset and identifies the fundamental performance traits of each of these techniques. The results provide valuable information to practitioners and researchers of predictive modeling by illustrating the performance of these algorithms on practical datasets in survival prediction tasks.