Prediksi Performa Akademik Siswa Menggunakan Machine Learning Berbasis Feature Engineering dan Explainable AI: Predicting Student Academic Performance Using Machine Learning with Feature Engineering and Explainable AI

Angger Haryo Putranto; Budi Prasetiyo

doi:10.57152/malcom.v6i4.2657

Authors

Angger Haryo Putranto Universitas Negeri Semarang
Budi Prasetiyo Universitas Negeri Semarang

DOI:

https://doi.org/10.57152/malcom.v6i4.2657

Keywords:

Explainable AI, Faktor Sosioekonomi, Feature Engineering, Machine Learning, Performa Akademik

Abstract

Perkembangan machine learning dalam bidang pendidikan memungkinkan pemanfaatan data untuk memprediksi performa akademik siswa sehingga dapat mendukung deteksi dini dan perumusan intervensi yang lebih tepat. Namun, sebagian penelitian masih berfokus pada peningkatan akurasi, sementara pengembangan representasi fitur berbasis pengetahuan domain (domain knowledge) untuk menggambarkan faktor sosioekonomi dan dukungan orang tua masih terbatas. Penelitian ini bertujuan untuk membangun model prediksi yang tidak hanya akurat tetapi juga mudah diinterpretasikan melalui integrasi feature engineering dan pendekatan Explainable Artificial Intelligence (XAI). Dataset yang digunakan terdiri dari 6.607 data siswa dengan 20 fitur. Tiga fitur baru dikembangkan, yaitu Study_Efficiency, Socioeconomic_Index, dan Parental_Support_Index. Selanjutnya, tujuh algoritma regresi dioptimasi menggunakan hyperparameter tuning dan dievaluasi berdasarkan Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), , serta 10-fold cross-validation. Hasil menunjukkan bahwa model Lasso memberikan performa terbaik dengan sebesar 0,7710 pada data uji dan 0,7392 0,1089 pada cross-validation. Analisis SHapley Additive exPlanations (SHAP) dan Partial Dependence Plot (PDP) menunjukkan bahwa faktor perilaku seperti Attendance dan Hours_Studied memiliki kontribusi yang lebih dominan, sementara fitur hasil rekayasa membantu merepresentasikan faktor sosioekonomi secara lebih terstruktur. Temuan ini menunjukkan bahwa model linear dengan representasi fitur yang sesuai dapat memberikan performa yang kompetitif sekaligus tetap transparan.

Downloads

Download data is not yet available.

References

Y. Lou and K. F. Colvin, “Performance prediction using educational data mining techniques?: a comparative study,” Discov. Educ., vol. 4, no. 1, p. 112, 2025, doi: 10.1007/s44217-025-00502-w.

M. N. Gul, W. Abbasi, and M. Y. Wani, “Revolutionizing educational decision ? making?: a robust machine learning mechanism for predicting student performance,” J. Electr. Syst. Inf Technol, vol. 12, no. 1, p. 32, 2025, doi: 10.1186/s43067-025-00230-z.

S. Boujmiraz, H. Darhmaoui, and A. Drissi, “Predicting student performance?: A comprehensive review of machine learning , deep learning , and explainable AI approaches,” Comput. Educ. Artif. Intell., vol. 10, p. 100548, 2026, doi: 10.1016/j.caeai.2026.100548.

Y. Guan, F. Wang, and S. Song, “Interpretable machine learning for academic performance prediction?: A SHAP-based analysis of key influencing factors,” Innov. Educ. Teach. Int., pp. 1–20, 2025, doi: 10.1080/14703297.2025.2532050.

M. Qiang, Z. Liu, and R. Zhang, “Explainable AI in education: integrating educational domain knowledge into the deep learning model for improved student performance prediction,” Sci. Rep., vol. 16, no. 1, p. 9515, 2026, doi: 10.1038/s41598-026-40538-y.

W. Ahmed, M. A. Wani, P. Plawiak, S. Meshoul, A. Mahmoud, and M. Hammad, “Machine learning-based academic performance prediction with explainability for enhanced decision-making in educational institutions,” Sci. Rep., vol. 15, no. 1, p. 26879, 2025, doi: 10.1038/s41598-025-12353-4.

B. Santana-Perera, C. García-Barceló, M. González Arcas, and D. Gil, “Exploring Predictive Insights on Student Success Using Explainable Machine Learning: A Synthetic Data Study,” Information, vol. 16, no. 9. p. 763, 2025. doi: 10.3390/info16090763.

O. O. Bifarin, “Interpretable machine learning with tree-based shapley additive explanations: Application to metabolomics datasets for binary classification.,” PLoS One, vol. 18, no. 5, p. e0284315, 2023, doi: 10.1371/journal.pone.0284315.

R. Wang, X. Wang, Z. Zhang, S. Zhang, and K. Li, “Research on the Nonlinear and Interactive Effects of Multidimensional Influencing Factors on Urban Innovation Cooperation: A Method Based on an Explainable Machine Learning Model,” Systems, vol. 13, no. 3. p. 187, 2025. doi: 10.3390/systems13030187.

A. Ichwani, R. Kesuma, A. Setiawan, I. Wicaksono, and R. Hanifah, “Preventing Data Leakage in Classification via Integrated Machine Learning Pipelines: Preprocessing, Feature Transformation, and Hyperparameter Tuning,” J. Tek. Inform., vol. 7, pp. 391–410, Feb. 2026, doi: 10.52436/1.jutif.2026.7.1.5490.

J. Addy, I. Anafo, and E. Westman, “The Role of EDA in Developing Robust Machine Learning Models for Lithology and Penetration Rate Prediction from MWD Data,” Mining, vol. 6, no. 1. p. 19, 2026. doi: 10.3390/mining6010019.

K. Maharana, S. Mondal, and B. Nemade, “A review: Data pre-processing and data augmentation techniques,” Glob. Transitions Proc., vol. 3, no. 1, pp. 91–99, 2022, doi: https://doi.org/10.1016/j.gltp.2022.04.020.

A. B. Bada, A. B. Garko, D. Gabi, and S. Musa, “The Role of Domain Knowledge in Feature Selection for Machine Learning,” J. Institutional Res. Big Data Anal. Innov., vol. 1, no. 3, pp. 180–187, 2025, doi: 10.5281/zenodo.16615428.

D. Retno, S. Saputro, N. L. Wahyu, and Y. Widyaningsih, “Performance of Ridge Regression, Least Absolute Shrinkage and Selection Operator, and Elastic Net in Overcoming Multicollinearity,” J. Multidiscip. Appl. Nat. Sci., vol. 5, no. 2, pp. 370–382, 2025, doi: https://doi.org/10.47352/jmans.2774-3047.251.

A. C. Cardall, R. C. Hales, K. B. Tanner, G. P. Williams, and K. N. Markert, “LASSO (L1) Regularization for Development of Sparse Remote-Sensing Models with Applications in Optically Complex Waters Using GEE Tools,” Remote Sensing, vol. 15, no. 6. p. 1670, 2023. doi: 10.3390/rs15061670.

K. Ko, A. Al Doulat, and S. Ku, “Ridge, LASSO, and elastic net regression?: Fathers ’ psychological well-being in familial contexts,” J. Soc. Pers. Relat., vol. 0, no. 0, pp. 1–26, 2025, doi: 10.1177/02654075251412474.

R. Guevara-Reyes, I. Ortiz-Garcés, R. Andrade, F. Cox-Riquetti, and W. Villegas-Ch, “Machine learning models for academic performance prediction: interpretability and application in educational decision-making,” Front. Educ., vol. Volume 10, 2025, doi: 10.3389/feduc.2025.1632315.

R. Shwartz-Ziv and A. Armon, “Tabular data: Deep learning is not all you need,” Inf. Fusion, vol. 81, pp. 84–90, 2022, doi: https://doi.org/10.1016/j.inffus.2021.11.011.

V. Teodorescu and L. Obreja Bra?oveanu, “Assessing the Validity of k-Fold Cross-Validation for Model Selection: Evidence from Bankruptcy Prediction Using Random Forest and XGBoost,” Computation, vol. 13, no. 5. p. 127, 2025. doi: 10.3390/computation13050127.

B. Hammoud, A. Semaan, L. Benova, and I. H. Elhajj, “A novel machine learning architecture to improve classification of intermediate cases in health: workflow and case study for public health,” BMC Bioinformatics, vol. 26, no. 1, p. 180, 2025, doi: 10.1186/s12859-025-06228-8.

M. Li, H. Sun, Y. Huang, and H. Chen, “Shapley value: from cooperative game to explainable artificial intelligence,” Auton. Intell. Syst., vol. 4, no. 1, p. 2, 2024, doi: 10.1007/s43684-023-00060-8.