Penerapan Regresi Robust dalam Educational Data Mining (EDM) untuk Klasifikasi Tingkat Penalaran Abduktif Siswa
DOI:
https://doi.org/10.29407/1457br77Keywords:
Educational Data Mining , regresi robust, klasifikasi, penalaran abduktif, pembelajaran matematikaAbstract
Penalaran abduktif merupakan salah satu bentuk penalaran tingkat tinggi yang berperan penting dalam pemecahan masalah matematika, namun masih sulit dianalisis secara objektif karena karakteristik data penilaian yang heterogen dan mengandung nilai ekstrem. Penelitian ini bertujuan mengimplementasikan regresi robust dalam kerangka Educational Data Mining (EDM) untuk mengklasifikasikan tingkat penalaran abduktif siswa SMP berdasarkan indikator penalaran yang terukur. Data diperoleh dari jawaban tertulis 72 siswa di SMP Negeri 3 Samaturu, Kabupaten Kolaka, yang dianalisis menggunakan rubrik analitik dengan delapan indikator penalaran abduktif. Regresi robust digunakan sebagai tahap estimasi fitur untuk mereduksi pengaruh outlier sebelum dilakukan klasifikasi tingkat penalaran ke dalam tiga kategori, yaitu rendah, sedang, dan tinggi, menggunakan pendekatan tertile-based threshold. Evaluasi model dilakukan dengan 5-fold cross validation dan diukur menggunakan metrik akurasi, precision, recall, dan F1-score, serta dibandingkan dengan model berbasis regresi linier konvensional (OLS). Hasil penelitian menunjukkan bahwa regresi robust menghasilkan kinerja klasifikasi yang lebih baik dan stabil dibandingkan OLS, dengan peningkatan pada seluruh metrik evaluasi. Distribusi klasifikasi menunjukkan 21 siswa berada pada tingkat rendah, 36 siswa pada tingkat sedang, dan 15 siswa pada tingkat tinggi. Penelitian ini menghasilkan bahwa integrasi regresi robust dalam EDM efektif untuk klasifikasi tingkat penalaran abduktif yang lebih akurat dan bermakna secara pedagogis
Downloads
References
[1]. OECD, PISA 2022 Results (Volume I): The State of Learning and Equity in Education, Paris, France: OECD Publishing, 2023, doi: 10.1787/53f23881-en.
[2]. P. J. Huber, “Robust estimation of a location parameter,” Annals of Mathematical Statistics, vol. 35, no. 1, pp. 73–101, 1964, doi: 10.1214/aoms/1177703732.
[3]. C. Romero and S. Ventura, “Educational data mining: A review of the state of the art,” IEEE Trans. Syst., Man, Cybern. C, vol. 40, no. 6, pp. 601–618, 2010, doi: 10.1109/TSMCC.2010.2053532.
[4]. E. Kalita et al., “Educational data mining: A 10-year review,” Discover Computing, vol. 28, no. 1, 2025, doi: 10.1007/s10791-025-09589-z.
[5]. H. Aldowah et al., “Educational data mining and learning analytics for 21st century higher education,” Telematics and Informatics, vol. 37, pp. 13–49, 2019, doi: 10.1016/j.tele.2019.01.007.
[6]. Yiyuni, N. Miftachurohmah, et al., “Expert system for identification of symptoms and diseases in lobsters using backward chaining,” Media of Computer Science, vol. 2, no. 1, pp. 37–50, 2025, doi: 10.69616/mcs.v2i1.232.
[7]. N. Nasruddin and N. Miftachurohmah, “The effect of integrative curriculum implementation and character education on academic success,” West Science Social and Humanities Studies, vol. 2, no. 8, pp. 1346–1354, 2024, doi: 10.58812/wsshs.v2i08.1192.
[8]. P. J. Rousseeuw and A. M. Leroy, Robust Regression and Outlier Detection. Hoboken, NJ, USA: Wiley, 2003, doi: 10.1002/0471725382.
[9]. M. Ilyas and S. Salahuddin, “An Evaluation of the Impact of Multicollinearity on the Performance of Various Robust Regression Methods,” Indian Journal of Science and Technology, vol. 12, no. 26, p. 1, Jul. 2019, doi: 10.17485/ijst/2019/v12i26/145300.
[10]. J. Kim and J. C. Li, “Which robust regression technique is appropriate under violated assumptions? A simulation study,” Methodology, vol. 19, no. 4, p. 323, Dec. 2023, doi: 10.5964/meth.8285.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Nasruddin Nasruddin, Nisa Miftachurohmah, Putri Rahayu Sianturi, Irnawati Irnawati, Iwan Iwan
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Copyright on any article is retained by the author(s).
- The author grants the journal, right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work’s authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal’s published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
- The article and any associated published material is distributed under the Creative Commons Attribution-ShareAlike 4.0 International License
