Claim Missing Document
Check
Articles

Mapping Potential New Student Admission Marketing Regions Using C4.5 and SVM with Multi-Method Feature Selection Maulana, Muhammad Sony; Prihastuti, Amini; Fitriyani, Vimi Putri; Wahyuningsih, Ratri; Ayu Safitri, Sri Dewi
JEPIN (Jurnal Edukasi dan Penelitian Informatika) Vol. 12 No. 2 (2026): Volume 12 No 2
Publisher : Program Studi Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

 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.
Co-Authors Abdul Latif Ade Muhammad Firman Hardiansyah Adrianus Ixnasius Bedong Agung Sasongko Agung Sasongko Ali Mustopa, Ali Almuhtadi Billah, Sabily Aprina, Tilawati Arnita Nonot Asterina, Yuly Badariatul Lailiah Diaz Arizona, Nanda Dido Khairulrijal Khairulrijal Elshie, Dwi Etania Frederika Fahreliandro, Zio febrina, anggi firmansyah, Yoki Fitri, Sabellah Ramadhiani Fitriyani, Vimi Putri Hendri Mahmud Nawawi Herman Kuswanto, Herman Ifan Rifani Ihsan, Muhammad Ifran Augitiansyah Indra Prasetya Kartika Handayani Handayani Laksono Trisnantoro Latifah Latifah Lisnawanty M. Rangga Ramadhan Saelan Miji Monica Julia Efata Monikka Nur Winnarto Muhamad Nasihin Muhamad Ryansyah Muhammad Ifan Rifani Ihsan Muhammad Iqbal Muhammad Iqbal Muhammad Nugi Sehpudin Saputra Muhammad Qadafi Khairuzzaman Ni Nyoman Cory Villdina Nur Aulia Hasanah Nurfia Oktaviani Syamsiah Nurjannah Nurjannah Nurmalasari Nurmalasari Nurmalasari Nurmalasari Nurmalasari Panny Agustia Rahayuningsih Permata, Ryan Cipta Prihastuti, Amini Purwandani, Indah Purwaningtias, Deasy Raja Sabaruddin Ravi Manisha Reza Maulana Reza Maulana Rezki, Muhammad Richo Dwi Wardiyanto Romadhon Risdiansyah, Deni Sabarudin, Raja Saiful Islam Sari Dewi Septian Rheno Widianto Shantika Trie Maharani Siti Khotimatul Wildah Siti Nurdiani Siti Rohmah Rohmah Sri Dewi Ayu Safitri Steven Sugeng Santoso Suharyanto Suharyanto Tarina Dashela Teguh Firmansyah Firmansyah Wahyu Nugraha Wahyuningsih, Ratri Wanty Eka Jayanti Wardiyanto Romadhon, Richo Dwi YANTO YANTO Yudhistira Yudhistira