<![CDATA[ Higher education institutions require effective and efficient marketing strategies to remain competitive in attracting prospective students. This study aims to identify potential regions for New Student Admission (NSA) marketing by comparing the Decision Tree (C4.5) and Support Vector Machine (SVM) algorithms while applying a multi-method feature selection approach consisting of the Chi-Square Test, Mutual Information, ANOVA F-Test, and Decision Tree Feature Importance to evaluate feature relevance prior to classification. The dataset consisted of 254 student records from Universitas Bina Sarana Informatika PSDKU Pontianak. The research workflow included data preprocessing, feature selection, an 80:20 train-test split, data balancing using Synthetic Minority Oversampling Technique (SMOTE), data normalization, classification modeling, and model evaluation using Stratified 10-Fold Cross-Validation with accuracy, precision, recall, F1-score, and ROC-AUC as performance metrics. The experimental results showed that the Decision Tree (C4.5) algorithm outperformed SVM, achieving an accuracy of 68.63%, precision of 71.56%, recall of 68.63%, F1-score of 68.34%, and ROC-AUC of 0.658. Feature selection identified the source of campus information, high school major, and study program as the most relevant attributes for classifying regional marketing potential. Furthermore, Pontianak and Kubu Raya were identified as the most promising promotional regions, while recommendations from relatives or family members and direct school visits emerged as the most influential promotional channels. The findings are expected to support the development of more effective, objective, and data-driven new student admission marketing strategies.]]>
