Pendekatan Ensemble Learning Untuk Meningkatkan Akurasi Prediksi Kinerja Akademik Mahasiswa
Article Sidebar
Main Article Content
Abstract
Penelitian ini bertujuan untuk meningkatkan akurasi prediksi kinerja mahasiswa dalam sistem pembelajaran virtual atau elearning menggunakan pendekatan ensemble learning. Dataset penelitian merupakan data publik berupa data log aktifitas elearning. Dataset yang telah melalui tahap pre processing, dimasukkan ke dalam pemodelan prediksi menggunakan gabungan beberapa algoritma pengklasifikasi yaitu Decision Tree, Random Forest, dan AdaBoost (ensemble learning). Tahap berikutnya mengevaluasi kinerja model dan menganalisis hasil prediksi menggunakan teknik root mean square error (RMSE). Output pemodelan berupa tiga level prediksi kinerja akademik (kelulusan mahasiswa) dalam sebuah course/semester, yaitu low-level, middle-level, dan high-level. Hasil pemodelan menunjukkan bahwa algoritma RF menghasilkan prediksi yang lebih akurat dibandingkan algoritma lainnya yaitu sebesar 75.79%, dengan RMSE mendekati 0 yaitu 0.44.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
References
[2] R. Conijn, C. Snijders, A. Kleingeld, and U. Matzat, “Predicting student performance from LMS data: A comparison of 17 blended courses using moodle LMS,†IEEE Trans. Learn. Technol., vol. 10, no. 1, pp. 17–29, 2017, doi: 10.1109/TLT.2016.2616312.
[3] S. Rakic, N. Tasic, U. Marjanovic, S. Softic, E. Lüftenegger, and I. Turcin, “Student performance on an e-learning platform: Mixed method approach,†Int. J. Emerg. Technol. Learn., vol. 15, no. 2, pp. 187–203, 2020, doi: 10.3991/ijet.v15i02.11646.
[4] Y. Abubakar, N. Bahiah, and H. Ahmad, “Prediction of Students’ Performance in E-Learning Environment Using Random Forest,†Int. J. Innov. Comput., vol. 7, no. 2, pp. 1–5, 2017, [Online]. Available: http://se.fsksm.utm.my/ijic/index.php/ijic
[5] S. A. Salloum, A. Qasim Mohammad Alhamad, M. Al-Emran, A. Abdel Monem, and K. Shaalan, “Exploring students’ acceptance of e-learning through the development of a comprehensive technology acceptance model,†IEEE Access, vol. 7, pp. 128445–128462, 2019, doi: 10.1109/ACCESS.2019.2939467.
[6] J. López-Zambrano, J. A. Lara, and C. Romero, “Towards portability of models for predicting students’ final performance in university courses starting from moodle logs,†Appl. Sci., vol. 10, no. 1, 2020, doi: 10.3390/app10010354.
[7] M. N. Injadat, A. Moubayed, A. B. Nassif, and A. Shami, “Systematic ensemble model selection approach for educational data mining,†Knowledge-Based Syst., vol. 200, p. 105992, 2020, doi: 10.1016/j.knosys.2020.105992.
[8] and S. M. S. Samuel-Soma M. Ajibade, Nor Bahiah Ahmad, A Data Mining Approach to Predict Academic Performance of Students Using Ensemble Techniques. Springer International Publishing, 2020. doi: 10.1007/978-3-030-16657-1.
[9] G. Liang and C. Zhang, “An Empirical Evaluation of Bagging with Different,†pp. 339–352, 2011.
[10] E. Alfaro, M. Gáamez, and N. GarcÃa, “Adabag: An R package for classification with boosting and bagging,†J. Stat. Softw., vol. 54, no. 2, 2013, doi: 10.18637/jss.v054.i02.
[11] C. Seiffert, T. M. Khoshgoftaar, J. Van Hulse, and A. Napolitano, “RUSBoost: Improving classification performance when training data is skewed,†Proc. - Int. Conf. Pattern Recognit., no. December, 2008, doi: 10.1109/icpr.2008.4761297.
[12] N. H. Harani, “Penerapan Adaboost Berbasis Pohon Keputusan Guna Menentukan Pola Masuknya Calon Mahasiswa Baru,†J. Transform., vol. 18, no. 1, p. 123, 2020, doi: 10.26623/transformatika.v18i1.1606.