A Hybrid Machine Learning Model for Predicting Engineering Student Placement with Explainable AI Techniques

— Prediction of the placement of students is one of the most critical activities for training organizations to optimize training programs and curricula based on industry demands. This paper suggests a Hybrid Prediction Model for placement prediction of engineering students based on recent Machine Learning (ML) techniques. It employs various ML strategies such as Decision Trees, Random Forest, Support Vector Machines (SVM), and Gradient Boosting with ensemble learning for achieving maximum accuracy and reliability of prediction. It uses a large Kaggle dataset for testing and training for practical purposes and different student profiles. Model performance is evaluated using accuracy, precision, recall, F1-score, and confusion matrices alongside training-validation loss plots for graphical analysis of performance. The proposed hybrid method has been found to achieve outstanding accuracy of 89 percent, which is significantly higher than individual models. Explainable AI (XAI) methodologies are also employed for interpretation of the model’s prediction to determine the most contributing factors of student placement. This paper demonstrates the potential of hybrid ML models as interpretable and effective tools for prediction of student placement to enable data-driven decision- making for training organizations and policymakers.