This project focuses on predicting student placement readiness using predictive analytics and machine learning techniques. The dataset was collected through Google Forms and includes academic, technical, and behavioral attributes such as CGPA, technical skills, communication ability, adaptability, internships, projects, and career interests. The data is preprocessed using Python libraries like Pandas and NumPy to handle missing values, extract numerical information, encode categorical variables, and scale features. A target variable, Placement_Ready, is created to classify students into placement-ready and not placement-ready categories.
Multiple machine learning models including Logistic Regression, K-Nearest Neighbors, Naive Bayes, Decision Tree, and Support Vector Machine (SVM) are trained and evaluated using performance metrics such as accuracy, precision, recall, F1-score, and log loss. Among all models, SVM achieved the best performance, making it the most reliable model for placement readiness prediction. The project also includes student clustering analysis and career interest–wise prediction insights, providing valuable decision support for educational institutions to enhance training and placement strategies.