Analisis Efektifitas Feature Selection dalam Pengkayaan Machine Learning untuk Deteksi Dini Risiko Putus Kuliah Mahasiswa
DOI:
https://doi.org/10.26418/jp.v11i1.90362Keywords:
Decision Tree, Random Forest, XGBoost, Optuna, Sequential Feature SelectorAbstract
Putus kuliah (dropout/ DO) mahasiswa merupakan masalah signifikan dalam pendidikan tinggi yang berdampak negatif pada institusi dan individu. Penelitian ini bertujuan mengevaluasi efektivitas metode feature selection dalam meningkatkan performa algoritma klasifikasi machine learning untuk memprediksi potensi mahasiswa putus kuliah. Penelitian ini berkontribusi dalam membantu otoritas perguruan tinggi dan pemangku kepentingan dalam memitigasi potensi putus kuliah mahasiswa. Penelitian ini menggunakan pendekatan Team Data Science Process (TDSP), meliputi pendefinisian tujuan, pengumpulan data, pemodelan, evaluasi, dan deployment. Dataset yang digunakan diperoleh dari data akademik Universitas Al Azhar Indonesia (UAI) periode 2015-2016 yang terdiri dari 1783 observasi dengan 13 fitur. Penelitian ini membandingkan metode feature selection seperti Optuna, Chi-squared, dan Sequential Feature Selector pada algoritma populer seperti Decision Tree, Random Forest, Naïve Bayes, dan XGBoost. Hasil evaluasi menunjukkan bahwa XGBoost dengan Selected Sequential Factor (SFS) adalah model yang paling direkomendasikan dengan akurasi 0,9565 dengan nilai precision, recall, dan f1-score yang konsisten di 0,96.References
M. Delogu, R. Lagravinese, D. Paolini, dan G. Resce, “Predicting dropout from higher education: Evidence from Italy,†Econ. Model., vol. 130, hlm. 106583, Jan 2024, doi: 10.1016/j.econmod.2023.106583.
PDDikti Kemendikbud, Statistik Pendidikan Tinggi Tahun 20222. Jakarta: Setditjen Dikti, Kemendikbud, 2022.
M. Vaarma dan H. Li, “Predicting student dropouts with machine learning: An empirical study in Finnish higher education,†Technol. Soc., vol. 76, hlm. 102474, Mar 2024, doi: 10.1016/j.techsoc.2024.102474.
J. Niyogisubizo, L. Liao, E. Nziyumva, E. Murwanashyaka, dan P. C. Nshimyumukiza, “Predicting student’s dropout in university classes using two-layer ensemble machine learning approach: A novel stacked generalization,†Comput. Educ. Artif. Intell., vol. 3, hlm. 100066, 2022, doi: 10.1016/j.caeai.2022.100066.
S. Sarker, M. K. Paul, S. T. H. Thasin, dan Md. A. M. Hasan, “Analyzing students’ academic performance using educational data mining,†Comput. Educ. Artif. Intell., vol. 7, hlm. 100263, Des 2024, doi: 10.1016/j.caeai.2024.100263.
S. Guzmán-Castillo dkk., “Implementation of a Predictive Information System for University Dropout Prevention,†Procedia Comput. Sci., vol. 198, hlm. 566–571, 2022, doi: 10.1016/j.procs.2021.12.287.
A. M. Rabelo dan L. E. Zárate, “A Model for Predicting Dropout of Higher Education Students,†Data Sci. Manag., hlm. S2666764924000341, Jul 2024, doi: 10.1016/j.dsm.2024.07.001.
A. M. Mariano, A. B. D. M. L. Ferreira, M. R. Santos, M. L. Castilho, dan A. C. F. L. C. Bastos, “Decision trees for predicting dropout in Engineering Course students in Brazil,†Procedia Comput. Sci., vol. 214, hlm. 1113–1120, 2022, doi: 10.1016/j.procs.2022.11.285.
D. Khairy, N. Alharbi, M. A. Amasha, M. F. Areed, S. Alkhalaf, dan R. A. Abougalala, “Prediction of student exam performance using data mining classification algorithms,†Educ. Inf. Technol., Mei 2024, doi: 10.1007/s10639-024-12619-w.
G. Al-Tameemi, J. Xue, I. H. Ali, dan S. Ajit, “A Hybrid Machine Learning Approach for Predicting Student Performance Using Multi-class Educational Datasets,†Procedia Comput. Sci., vol. 238, hlm. 888–895, 2024, doi: 10.1016/j.procs.2024.06.108.
T. Wahyuningsih, D. Manongga, I. Sembiring, dan S. Wijono, “Comparison of Effectiveness of Logistic Regression, Naive Bayes, and Random Forest Algorithms in Predicting Student Arguments,†Procedia Comput. Sci., vol. 234, hlm. 349–356, 2024, doi: 10.1016/j.procs.2024.03.014.
S. D. A. Bujang dkk., “Multiclass Prediction Model for Student Grade Prediction Using Machine Learning,†IEEE Access, vol. 9, hlm. 95608–95621, 2021, doi: 10.1109/ACCESS.2021.3093563.
O. Peretz, M. Koren, dan O. Koren, “Naive Bayes classifier – An ensemble procedure for recall and precision enrichment,†Eng. Appl. Artif. Intell., vol. 136, hlm. 108972, Okt 2024, doi: 10.1016/j.engappai.2024.108972.
A. López-GarcÃa, O. Blasco-Blasco, M. Liern-GarcÃa, dan S. E. Parada-Rico, “Early detection of students’ failure using Machine Learning techniques,†Oper. Res. Perspect., vol. 11, hlm. 100292, Des 2023, doi: 10.1016/j.orp.2023.100292.
P. Xuan Lam, P. Q. H. Mai, Q. H. Nguyen, T. Pham, T. H. H. Nguyen, dan T. H. Nguyen, “Enhancing educational evaluation through predictive student assessment modeling,†Comput. Educ. Artif. Intell., vol. 6, hlm. 100244, Jun 2024, doi: 10.1016/j.caeai.2024.100244.
P. R., K. P., dan S. A. A., “Predicting academic performance of learners with the three domains of learning data using neuro-fuzzy model and machine learning algorithms,†J. Eng. Res., vol. 12, no. 3, hlm. 397–411, Sep 2024, doi: 10.1016/j.jer.2023.09.006.
M. K. Hossen dan M. S. Uddin, “Attention monitoring of students during online classes using XGBoost classifier,†Comput. Educ. Artif. Intell., vol. 5, hlm. 100191, 2023, doi: 10.1016/j.caeai.2023.100191.
J. Pecuchova dan M. Drlik, “Predicting Students at Risk of Early Dropping Out from Course Using Ensemble Classification Methods,†Procedia Comput. Sci., vol. 225, hlm. 3223–3232, 2023, doi: 10.1016/j.procs.2023.10.316.
K. Roy dan D. Md. Farid, “An Adaptive Feature Selection Algorithm for Student Performance Prediction,†IEEE Access, vol. 12, hlm. 75577–75598, 2024, doi: 10.1109/ACCESS.2024.3406252.
Universitas Amikom Purwwokerto dkk., “Optuna Based Hyperparameter Tuning for Improving the Performance Prediction Mortality and Hospital Length of Stay for Stroke Patients,†Telematika, vol. 17, no. 1, hlm. 1–16, Feb 2024, doi: 10.35671/telematika.v17i1.2816.
F. Mohtasham, M. Pourhoseingholi, S. S. Hashemi Nazari, K. Kavousi, dan M. R. Zali, “Comparative analysis of feature selection techniques for COVID-19 dataset,†Sci. Rep., vol. 14, no. 1, hlm. 18627, Agu 2024, doi: 10.1038/s41598-024-69209-6.
K. Chotchantarakun, “Optimizing Sequential Forward Selection on Classification Using Genetic Algorithm,†Informatica, vol. 47, hlm. 81–90, Jun 2023, doi: https://doi.org/10.31449/inf.v47i9.4964.
Y. Liu, Y. Hui, D. Hou, dan X. Liu, “A Novel Student Achievement Prediction Method Based on Deep Learning and Attention Mechanism,†IEEE Access, vol. 11, hlm. 87245–87255, 2023, doi: 10.1109/ACCESS.2023.3305248.
D. Sobnath, T. Kaduk, I. U. Rehman, dan O. Isiaq, “Feature Selection for UK Disabled Students’ Engagement Post Higher Education: A Machine Learning Approach for a Predictive Employment Model,†IEEE Access, vol. 8, hlm. 159530–159541, 2020, doi: 10.1109/ACCESS.2020.3018663.
E.-Y. Seo, J. Yang, J.-E. Lee, dan G. So, “Predictive modelling of student dropout risk: Practical insights from a South Korean distance university,†Heliyon, vol. 10, no. 11, hlm. e30960, Jun 2024, doi: 10.1016/j.heliyon.2024.e30960.
D. Liu, Y. Zhang, J. Zhang, Q. Li, C. Zhang, dan Y. Yin, “Multiple Features Fusion Attention Mechanism Enhanced Deep Knowledge Tracing for Student Performance Prediction,†IEEE Access, vol. 8, hlm. 194894–194903, 2020, doi: 10.1109/ACCESS.2020.3033200.
D. Goller, A. Diem, dan S. C. Wolter, “Sitting next to a dropout: Academic success of students with more educated peers,†Econ. Educ. Rev., vol. 93, hlm. 102372, Apr 2023, doi: 10.1016/j.econedurev.2023.102372.
S. Limanto, J. L. Buliali, dan A. Saikhu, “GLoW SMOTE-D: Oversampling Technique to Improve Prediction Model Performance of Students Failure in Courses,†IEEE Access, vol. 12, hlm. 8889–8901, 2024, doi: 10.1109/ACCESS.2024.3351
