Klasifikasi Prestasi Akademik Matematika Siswa Menggunakan Decision Tree pada Dataset Student Performance

Elisabeth Jessica Sitanggang; Yeheskiel Ravena Damanik; Esther Laura Rumahorbo; Albert Adolf Angie MS

doi:10.31004/riggs.v5i2.12193

Authors

Elisabeth Jessica Sitanggang Universitas HKBP Nommensen Pematangsiantar
Yeheskiel Ravena Damanik Universitas HKBP Nommensen Pematangsiantar
Esther Laura Rumahorbo Universitas HKBP Nommensen Pematangsiantar
Albert Adolf Angie MS Universitas HKBP Nommensen Pematangsiantar

DOI:

https://doi.org/10.31004/riggs.v5i2.12193

Keywords:

Prestasi Akademik, Klasifikasi, Decision Tree, Penambangan Data Pendidikan, Orange Data Mining, Dataset Student Performance

Abstract

Klasifikasi prestasi akademik dapat membantu sekolah mengidentifikasi siswa yang memerlukan perhatian dan dukungan pembelajaran secara lebih terarah. Penelitian ini bertujuan menerapkan algoritma Decision Tree untuk mengklasifikasikan prestasi akademik matematika siswa menggunakan dataset Student Performance yang diperoleh dari Kaggle dan bersumber dari UCI Machine Learning Repository. Dataset terdiri atas 395 data siswa dengan atribut demografis, keluarga, sekolah, sosial, perilaku, dan akademik. Variabel target dibentuk dari nilai akhir matematika G3 menjadi tiga kategori, yaitu Rendah untuk nilai 0-9, Sedang untuk nilai 10-14, dan Tinggi untuk nilai 15-20. Variabel G3 tidak digunakan sebagai prediktor guna mencegah kebocoran data, sedangkan G1 dan G2 tetap digunakan untuk merepresentasikan capaian akademik sebelumnya. Pemodelan dilakukan menggunakan Orange Data Mining dengan kedalaman maksimum pohon lima, minimum lima data pada setiap daun, dan kriteria penghentian ketika mayoritas kelas mencapai 95%. Evaluasi dilakukan melalui validasi silang 10 lipatan terstratifikasi menggunakan metrik AUC, akurasi, presisi, recall, F1-score, dan Matthews Correlation Coefficient. Hasil pengujian menunjukkan nilai AUC sebesar 0,934, akurasi 0,871, presisi 0,871, recall 0,871, F1-score 0,871, dan MCC 0,791. Confusion matrix menunjukkan 344 dari 395 data diklasifikasikan dengan benar. Struktur pohon menempatkan G2 sebagai atribut pemisah utama, diikuti G1 dan beberapa atribut pendukung. Temuan ini menunjukkan bahwa Decision Tree mampu menghasilkan klasifikasi yang akurat, transparan, dan mudah diinterpretasikan untuk mendukung analisis prestasi matematika siswa setelah nilai periode pertama dan kedua tersedia.

Downloads

Download data is not yet available.

References

[1] C. Romero and S. Ventura, "Educational data mining and learning analytics: An updated survey," WIREs Data Mining and Knowledge Discovery, vol. 10, e1355, 2020, doi: 10.1002/widm.1355.

[2] E. Alyahyan and D. Düştegör, "Predicting academic success in higher education: Literature review and best practices," International Journal of Educational Technology in Higher Education, vol. 17, art. 3, 2020, doi: 10.1186/s41239-020-0177-7.

[3] P. Cortez and A. M. G. Silva, "Using data mining to predict secondary school student performance," in Proceedings of the 5th Future Business Technology Conference (FUBUTEC 2008), A. Brito and J. Teixeira, Eds., Porto, Portugal, Apr. 2008, pp. 5-12.

[4] P. Cortez, "Student Performance," UCI Machine Learning Repository, 2014, doi: 10.24432/C5TG7T.

[5] L. Breiman, J. H. Friedman, R. A. Olshen, and C. J. Stone, Classification and Regression Trees. Belmont, CA, USA: Wadsworth International Group, 1984.

[6] J. Demšar et al., "Orange: Data Mining Toolbox in Python," Journal of Machine Learning Research, vol. 14, pp. 2349-2353, 2013.

[7] R. Kohavi, "A study of cross-validation and bootstrap for accuracy estimation and model selection," in Proceedings of the 14th International Joint Conference on Artificial Intelligence (IJCAI 1995), Montreal, QC, Canada, 1995, pp. 1137-1143.

[8] T. Fawcett, "An introduction to ROC analysis," Pattern Recognition Letters, vol. 27, no. 8, pp. 861-874, 2006, doi: 10.1016/j.patrec.2005.10.010.

[9] J. Gorodkin, "Comparing two K-category assignments by a K-category correlation coefficient," Computational Biology and Chemistry, vol. 28, no. 5-6, pp. 367-374, 2004, doi: 10.1016/j.compbiolchem.2004.09.006.

[10] J. R. Quinlan, "Induction of decision trees," Machine Learning, vol. 1, pp. 81-106, 1986, doi: 10.1007/BF00116251.

[11] H. He and E. A. Garcia, "Learning from imbalanced data," IEEE Transactions on Knowledge and Data Engineering, vol. 21, no. 9, pp. 1263-1284, 2009, doi: 10.1109/TKDE.2008.239.

[12] M. Yağcı, "Educational data mining: prediction of students’ academic performance using machine learning algorithms," Smart Learning Environments, vol. 9, art. no. 11, 2022, doi: 10.1186/s40561-022-00192-z.

[13] A. Khan and S. K. Ghosh, "Student performance analysis and prediction in classroom learning: A review of educational data mining studies," Education and Information Technologies, vol. 26, pp. 205–240, 2021, doi: 10.1007/s10639-020-10230-3.

[14] D. Khairy, N. Alharbi, M. A. Amasha, M. F. Areed, S. Alkhalaf, and R. A. Abougalala, "Prediction of student exam performance using data mining classification algorithms," Education and Information Technologies, vol. 29, pp. 21621–21645, 2024, doi: 10.1007/s10639-024-12619-w.

[15] Z. Ersozlu, S. Taheri, and I. Koch, "A review of machine learning methods used for educational data," Education and Information Technologies, vol. 29, pp. 22125–22145, 2024, doi: 10.1007/s10639-024-12704-0.

[16] M. M. Islam, F. H. Sojib, M. F. H. Mihad, M. Hasan, and M. Rahman, "The integration of explainable AI in Educational Data Mining for student academic performance prediction and support system," Telematics and Informatics Reports, vol. 18, art. no. 100203, 2025, doi: 10.1016/j.teler.2025.100203.