An ML-driven decision support system for engineering college selection post-intermediate education in India

The paper is a developed machine learning-based decision support system that will guide the choice of an engineering college by intermediate (10+2) students in India in accordance with their academic backgrounds, individual preferences and institutional characteristics. The model combines information that is heterogeneous, such as entrance exam scores, college ratings, placement scores, accreditation, tuition costs, geographic orientation and alumni responses to create customized college suggestions. Decision Tree, Random Forest, Support Vector Machine (SVM), k-Nearest Neighbours (KNN) and Logistic Regression. Five machine learning algorithms were trained and tested to determine which predictive model is most efficient. The best of them was the Random Forest algorithm, which obtained the highest accuracy, with 87.3, and an F1-score of 0.85, showing the best generalization and strengths. Furthermore, a hybrid recommendation scheme that incorporates both content-based and collaborative filtering strategies was introduced to increase the personalization and to adequately address the issue of cold-start. The system suggested can be scaled to support the large-scale implementation and provide scalability, interpretability, and flexibility in a wide range of educational settings. The results of the experiments prove that the hybrid framework has greater precision and recall than standalone recommendation models. This study fills an important gap in automated educational guidance by offering a transparent, unbiased and data-driven decision support system to the student, counsellors and policy makers. The created architecture represents a groundbreaking move to incorporate artificial intelligence and predictive analytics in the educational planning, which will make the process of college selection informed, equitable, and evidence-based and will make college selection available to aspiring engineering students in India.