Scholarships are critical in making education accessible to students from diverse socio-economic backgrounds. This research aimed to develop a multi-label classification-based scholarship recommendation system for engineering students in India. Utilizing a dataset of dummy students and scholarships, various multi-label classification models were evaluated, including Binary Relevance, Classifier Chains, Label Powerset, Multi-Output Classifier (MOC) with Random Forest, Multi-Output Classifier (MOC) with KNeighbors and Multi-Label k-Nearest Neighbors. Models were assessed based on F1 Scores, Jaccard Scores, Accuracy, and Hamming Loss. The Random Forest model emerged as the top performer with the highest accuracy of 88% and lowest Hamming Loss of 0.009, followed by KNeighbors and Multi-Label KNN as strong alternatives. The study highlights the effectiveness of multi-label classification in enhancing scholarship recommendation systems, providing a robust tool to support students in identifying suitable scholarship opportunities.