This project addresses a critical business problem in Human Resources: predicting and preventing employee turnover using machine learning and data visualization techniques. The workflow includes data preprocessing, handling class imbalance with SMOTEENN, and applying various supervised learning models such as Random Forest, SVM, Logistic Regression, KNN, Decision Tree, AdaBoost, XGBoost, LDA, QDA, and Gradient Boosting. Hyperparameter optimization was conducted using GridSearchCV and RandomizedSearchCV. Key insights were visualized using Tableau to support strategic HR decision-making and retention planning.