In the field of education, student enrollment prediction has been a crucial task for universities and colleges to make informed decisions. This study aims to investigate the effectiveness of classification algorithms in predicting student enrollment. A dataset containing demographic information and academic records of past students was used to train and test six different classification algorithms implemented in WEKA, a popular data mining tool. The algorithms included in this study were J48 (C4.5), Naive Bayes, Random Forest, IBk (k-nearest neighbor), JRIP and Logistic Regression. The performance of each algorithm was evaluated using several performance metrics, including accuracy, precision, recall, F1-score, and ROC AUC. The results showed that Random Forest outperformed the other algorithms in terms of accuracy, precision, recall, F1-score, and ROC AUC. This study demonstrates the effectiveness of using classification algorithms in predicting student enrollment and highlights the importance of considering multiple performance metrics in evaluating the performance of these algorithms.