Implementasi Metode MOORA Berbobot untuk Pemeringkatan Model Machine Learning pada Deteksi Mahasiswa Berisiko Dropout

Izzar Suly Nashrudin, Elif Thoyyibah Rahmawati, Nur Intan Aprilia, Siti Syarifah Jamalia, Dzikry Fikrillah, Risma Muslimah

Abstract


Tingkat dropout pada mahasiswa di perguruan tinggi menjadi tantangan nyata yang tidak langsung mengancam reputasi institusi, dan masa depan mahasiswa itu sendiri. Prediksi menggunakan machine learning telah berkembang pesat, tetapi evaluasi model terkadang bergantung pada metrik akurasi dan tanpa mempertimbangkan sumber daya seperti waktu komputasi dan ukuran model. Tujuan riset untuk merancang pengambilan keputusan multikriteria menggunakan Multi-Objective Optimization on the Basis of Ratio Analysis (MOORA) untuk memeringkat model prediksi dropout seperti Logistic Regression, Gaussian Naive Bayes, KNN, Decision Tree, Random Forest, SVM, LDA, dan QDA. Penelitian menggunakan platfrom Kaggle berbasis CPU Multi-Thread dengan 4 seed dan 10 kali perulangan per seed. Dengan kriteria keuntungan (akurasi, presisi, recall, F1-score, dan ROC-AUC) dan kriteria biaya (log loss, waktu komputasi, ukuran model, FPR, dan FNR). Hasil riset menunjukkan Logistic Regression menduduki peringkat pertama dengan Y1 = 0,170760, diikuti LDA dengan Y7 = 0,167518 dan QDA dengan Y8 = 0,109363. Random Forest turun ke peringkat ketujuh akibat biaya komputasi dan ukuran model tinggi. Pada skenario inferensi 794 mahasiswa Enrolled, tiga model teratas memprediksi 30,23%–53,65% mahasiswa berisiko dropout. Penelitian ini dirancang untuk seleksi model yang layak operasional dan hemat sumber daya untuk sistem peringatan dini akademik.

Keywords


dropout; keputusan; machine learning; MCDM; mahasiswa; MOORA

Full Text:

PDF - ID

References


E. A. Adali and A. T. Isik, “The multi-objective decision making methods based on MULTIMOORA and MOOSRA for the laptop selection problem,” Journal of Industrial Engineering International, vol. 13, no. 2, pp. 229–237, 2017. DOI: 10.1007/s40092-016-0175-5.

D. Andrade-Girón, J. Sandivar-Rosas, W. Marín-Rodriguez, E. Susanibar-Ramirez, E. Toro-Dextre, J. Ausejo-Sanchez, H. Villarreal-Torres, and J. Angeles-Morales, “Predicting student dropout based on machine learning and deep learning: A systematic review,” EAI Endorsed Transactions on Scalable Information Systems, vol. 10, no. 5, 2023. DOI: 10.4108/eetsis.3586.

J. Berens, K. Schneider, S. Görtz, S. Oster, and J. Burghoff, “Early detection of students at risk: Predicting student dropouts using administrative student data from German universities and machine learning methods,” Journal of Educational Data Mining, vol. 11, no. 3, pp. 1–41, 2019. DOI: 10.5281/zenodo.3594771.

W. K. M. Brauers and E. K. Zavadskas, “The MOORA method and its application to privatization in a transition economy,” Control and Cybernetics, vol. 35, no. 2, pp. 445–469, 2006.

S. Chakraborty, H. N. Datta, K. Kalita, and S. Chakraborty, “A narrative review of multi-objective optimization on the basis of ratio analysis (MOORA) method in decision making,” OPSEARCH, vol. 60, no. 4, pp. 1844–1887, 2023. DOI: 10.1007/s12597-023-00676-7.

H. Chavez, B. Chavez-Arias, S. Contreras-Rosas, J. M. Alvarez-Rodríguez, and C. Raymundo, “Artificial neural network model to predict student performance using nonpersonal information,” Frontiers in Education, vol. 8, p. 1106679, 2023. DOI: 10.3389/feduc.2023.1106679.

C. H. Cho, Y. W. Yu, and H. G. Kim, “A study on dropout prediction for university students using machine learning,” Applied Sciences, vol. 13, no. 21, p. 12004, 2023. DOI: 10.3390/app132112004.

B. Duro, A. Gomes, F. B. Correia, A. R. Borges, and J. Bernardino, “Machine learning and deep learning for dropout prediction in higher education: A review,” Computers, vol. 15, no. 3, p. 164, 2026. DOI: 10.3390/computers15030164.

Y. Efendi, “Machine learning-based classification of student adaptability in online learning with feature engineering,” TIERS Information Technology Journal, vol. 6, no. 1, pp. 129–143, 2025. DOI: 10.38043/tiers.v6i1.6806.

R. A. Fisher, “The use of multiple measurements in taxonomic problems,” Annals of Eugenics, vol. 7, no. 2, pp. 179–188, 1936. DOI: 10.1111/j.1469-1809.1936.tb02137.x.

J. H. Friedman, “Regularized discriminant analysis,” Journal of the American Statistical Association, vol. 84, no. 405, pp. 165–175, 1989. DOI: 10.1080/01621459.1989.10478752.

T. Gneiting and A. E. Raftery, “Strictly proper scoring rules, prediction, and estimation,” Journal of the American Statistical Association, vol. 102, no. 477, pp. 359–378, 2007. DOI: 10.1198/016214506000001437.

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.

N. Hidayat, L. Afuan, and H. R. Jannah, “Prescriptive learning analytics for student dropout: Integrating temporal velocity and counterfactual explanations in longitudinal data,” Journal of Computing Theories and Applications, vol. 3, no. 4, pp. 627–646, 2026. DOI: 10.62411/jcta.15920.

S. Lee and J. Y. Chung, “The machine learning-based dropout early warning system for improving the performance of dropout prediction,” Applied Sciences, vol. 9, no. 15, p. 3093, 2019. DOI: 10.3390/app9153093.

S. Leelaluk, C. Tang, V. Švábenský, and A. Shimada, “Knowledge distillation in RNN-attention models for early prediction of student performance,” in Proceedings of the 40th ACM/SIGAPP Symposium on Applied Computing, SAC ’25, New York, NY, USA: Association for Computing Machinery, 2025. DOI: 10.1145/3672608.3707805.

O. Ovtšarenko, “Using AI to forecast student dropout risk in technical education using a learning analytics approach,” Scientific Reports, vol. 16, p. 14616, 2026. DOI: 10.1038/s41598-026-44919-1.

D. Preuveneers, I. Tsingenopoulos, and W. Joosen, “Resource usage and performance trade-offs for machine learning models in smart environments,” Sensors, vol. 20, no. 4, p. 1176, 2020. DOI: 10.3390/s20041176.

M. N. Razooqee and M. A. H. Ashour, “Application of multi-objective optimization on the basis of ratio analysis (MOORA) method,” Journal of Economics and Administrative Sciences, vol. 26, no. 122, pp. 412–421, 2020. DOI: 10.33095/jeas.v26i122.2016.

V. Realinho, M. Vieira Martins, J. Machado, and L. Baptista, Predict Students’ Dropout and Academic Success, UCI Machine Learning Repository, [Dataset], 2021. DOI: 10.24432/C5MC89.

R. D. Romdhoni, N. W. A. Majid, and A. F. Permatasari, “Machine learning-based early warning for student dropout: Evidence from LMS behavioral engagement patterns in online higher education,” Journal of Informatics and Vocational Education, vol. 9, no. 2, pp. 55–66, Jul. 2026. DOI: 10.20961/joive.v9i2.3508.

T. Saito and M. Rehmsmeier, “The precision-recall plot is more informative than the ROC plot when evaluating binary classifiers on imbalanced datasets,” PLOS ONE, vol. 10, no. 3, p. e0118432, 2015. DOI: 10.1371/journal.pone.0118432.




DOI: https://doi.org/10.18860/jrmm.v6i2.43376

Refbacks

  • There are currently no refbacks.