Analisis Komparatif Algoritma Decision Tree dan Random Forest untuk Prediksi Kelulusan Mahasiswa

Yuce Yuliani

doi:10.31004/riggs.v5i2.10534

Authors

Yuce Yuliani Universitas Gunadarma

DOI:

https://doi.org/10.31004/riggs.v5i2.10534

Keywords:

Random Forest, Decision Tree, Prediksi Kelulusan Mahasiswa, Educational Data Mining, Feature Importance

Abstract

Prediksi kelulusan mahasiswa merupakan salah satu upaya strategis yang dapat dilakukan perguruan tinggi untuk meningkatkan kualitas layanan akademik, mengidentifikasi mahasiswa yang berpotensi mengalami keterlambatan studi, serta mengurangi risiko dropout melalui pemberian intervensi akademik secara lebih dini. Pemanfaatan teknik data mining dan machine learning memungkinkan institusi pendidikan menghasilkan model prediksi yang akurat sebagai dasar pengambilan keputusan berbasis data. Penelitian ini bertujuan untuk membandingkan kinerja algoritma Decision Tree dan Random Forest dalam memprediksi kelulusan mahasiswa menggunakan dataset Predict Students' Dropout and Academic Success yang diperoleh dari UCI Machine Learning Repository. Dataset awal terdiri atas 4.424 data mahasiswa dengan 37 atribut yang mencakup karakteristik akademik, demografis, dan sosial ekonomi. Setelah melalui tahapan preprocessing yang meliputi pembersihan data, seleksi kelas, dan penanganan data yang tidak relevan, diperoleh 3.630 data yang digunakan dalam proses pemodelan. Data kemudian dibagi menjadi data pelatihan sebesar 80% dan data pengujian sebesar 20%. Evaluasi performa model dilakukan menggunakan metrik accuracy, precision, recall, dan F1-score. Hasil penelitian menunjukkan bahwa algoritma Random Forest memiliki performa yang lebih baik dibandingkan Decision Tree dengan nilai accuracy sebesar 91,46%, sedangkan Decision Tree memperoleh accuracy sebesar 85,81%. Analisis feature importance menunjukkan bahwa variabel akademik, terutama Curricular Units 2nd Sem (Approved) dan Curricular Units 2nd Sem (Grade), merupakan faktor yang paling berpengaruh terhadap kelulusan mahasiswa. Temuan ini menunjukkan bahwa Random Forest merupakan model yang efektif untuk memprediksi kelulusan mahasiswa dan berpotensi diimplementasikan sebagai bagian dari sistem peringatan dini guna mendukung peningkatan keberhasilan studi di perguruan tinggi.

Downloads

Download data is not yet available.

References

[1] A. Nazyrova, M. Miłosz, G. Bekmanova, A. Omarbekova, G. Aimicheva, and Y. Kadyr, “The Digital Transformation of Higher Education in the Context of an AI-Driven Future,” Sustainability, vol. 17, no. 22, p. 9927, Nov. 2025, doi: 10.3390/su17229927.

[2] Y. Liu, N. Tuerdahong, and B. Wang, “Research on the Optimization Path of College Education and Teaching Based on Big Data Analysis,” Applied Mathematics and Nonlinear Sciences, vol. 9, no. 1, Jan. 2024, doi: 10.2478/amns-2024-2862.

[3] P. Basavaraj and I. Garibay, “Dropout vs. Time to Degree,” in Proceedings of the 20th Annual SIG Conference on Information Technology Education, New York, NY, USA: ACM, Sep. 2019, pp. 154–154. doi: 10.1145/3349266.3351374.

[4] A. Viloria, A. Senior Naveda, H. Hernández Palma, W. Niebles Núñez, and L. Niebles Núñez, “Using Big Data to Determine Potential Dropouts in Higher Education,” J. Phys. Conf. Ser., vol. 1432, no. 1, p. 012077, Jan. 2020, doi: 10.1088/1742-6596/1432/1/012077.

[5] F. Irhamna Rachman, S. Mujadilah, T. Wahyuni, and L. Anas, “Prediksi Tingkat Kelulusan Menggunakan K-Means Pada Program Studi Informatika Unismuh Makassar,” JURNAL FASILKOM, vol. 13, no. 3, pp. 504–510, Dec. 2023, doi: 10.37859/jf.v13i3.6061.

[6] S. Abdillah, G. Juni Yanris, and V. Sihombing, “Implementation of the Support Vector Machine Method in Predicting Student Graduation,” International Journal of Science, Technology & Management, vol. 5, no. 4, pp. 1036–1043, Aug. 2024, doi: 10.46729/ijstm.v5i4.1140.

[7] M. C. Dinh, V. T. Ha, and D. H. Dinh, “A Comparative Analysis of Machine Learning and Deep Learning Models for Student On-Time Graduation Prediction,” in 2025 IEEE International Conference on Emerging Trends in Engineering and Computing (ETECOM), IEEE, Oct. 2025, pp. 1–7. doi: 10.1109/ETECOM66111.2025.11319063.

[8] P. Ghosh, R. Roy, S. Mandal, M. Chowdhary, and S. Bokshi, “Data mining approach to predict academic performanceof students,” BOHR International Journal of Smart Computing and Information Technology, vol. 4, no. 1, pp. 39–49, 2023, doi: 10.54646/bijscit.2023.35.

[9] S. Alturki, I. Hulpuș, and H. Stuckenschmidt, “Predicting Academic Outcomes: A Survey from 2007 Till 2018,” Technology, Knowledge and Learning, vol. 27, no. 1, pp. 275–307, Mar. 2022, doi: 10.1007/s10758-020-09476-0.

[10] K. Alalawi, R. Athauda, and R. Chiong, “Contextualizing the current state of research on the use of machine learning for student performance prediction: A systematic literature review,” Engineering Reports, vol. 5, no. 12, Dec. 2023, doi: 10.1002/eng2.12699.

[11] R. Qureshi and P. S. Lokhande, “A Comprehensive Review of Machine Learning techniques used for Designing An Academic Result Predictor And Identifying The Multi-Dimensional Factors Affecting Student’s Academic Results,” in 2024 2nd DMIHER International Conference on Artificial Intelligence in Healthcare, Education and Industry (IDICAIEI), IEEE, Nov. 2024, pp. 1–6. doi: 10.1109/IDICAIEI61867.2024.10842901.

[12] W. Yustanti, R. E. Putra, I. Gusti Putu Asto Buditjahjanto, and A. I. Nurhidayat, “Exploring Ensemble Classifiers and Filter-Based Feature Selection for Predicting On-Time Graduation Using Multidimensional Student Data,” in 2025 Eight International Conference on Vocational Education and Electrical Engineering (ICVEE), IEEE, Sep. 2025, pp. 246–251. doi: 10.1109/ICVEE66651.2025.11281493.

[13] I. P. Y. T. Sugitha, F. A. Bachtiar, and S. A. Wicaksono, “Application of Students Graduation Prediction Model Using Decision Tree C4.5 Algorithm and Synthetic Minority Oversampling Technique (SMOTE),” in 2024 Seventh International Conference on Vocational Education and Electrical Engineering (ICVEE), IEEE, Oct. 2024, pp. 175–181. doi: 10.1109/ICVEE63912.2024.10823806.

[14] M. N. Gul, W. Abbasi, M. Z. Babar, A. Aljohani, and M. Arif, “Data driven decisions in education using a comprehensive machine learning framework for student performance prediction,” Discover Computing, vol. 28, no. 1, p. 153, Jul. 2025, doi: 10.1007/s10791-025-09585-3.

[15] S. Neththikumara and M. W. P. Maduranga, “Recent Results of Machine Learning in Predicting Student Performance: A Systematic Literature Review,” in 2025 IEEE Digital Education and MOOCS Conference (DEMOcon), IEEE, Oct. 2025, pp. 1–5. doi: 10.1109/DEMOcon65705.2025.11282820.

[16] J. Zhao, C.-D. Lee, G. Chen, and J. Zhang, “Research on the Prediction Application of Multiple Classification Datasets Based on Random Forest Model,” in 2024 IEEE 6th International Conference on Power, Intelligent Computing and Systems (ICPICS), IEEE, Jul. 2024, pp. 156–161. doi: 10.1109/ICPICS62053.2024.10795875.

[17] Z. Feng, Y. Shi, D. Zhou, and L. Mo, “Research on Human Activity Recognition Based on Random Forest Classifier,” in 2023 IEEE International Conference on Control, Electronics and Computer Technology (ICCECT), IEEE, Apr. 2023, pp. 1507–1513. doi: 10.1109/ICCECT57938.2023.10140545.

[18] M. Maindola et al., “Utilizing Random Forests for High-Accuracy Classification in Medical Diagnostics,” in 2024 7th International Conference on Contemporary Computing and Informatics (IC3I), IEEE, Sep. 2024, pp. 1679–1685. doi: 10.1109/IC3I61595.2024.10828609.

[19] J. Zhao, C.-D. Lee, G. Chen, and J. Zhang, “Research on the Prediction Application of Multiple Classification Datasets Based on Random Forest Model,” in 2024 IEEE 6th International Conference on Power, Intelligent Computing and Systems (ICPICS), IEEE, Jul. 2024, pp. 156–161. doi: 10.1109/ICPICS62053.2024.10795875.

[20] J. Casanova, J. Sinval, and L. Almeida, “Academic success, engagement and self-efficacy of first-year university students: personal variables and first-semester performance,” Anales de Psicología, vol. 40, no. 1, pp. 44–53, Jan. 2024, doi: 10.6018/analesps.479151.