Analisis Prediksi Kelulusan Mahasiswa Universitas Sultan Ageng Tirtayasa Menggunakan Algoritma Machine Learning dan Feature Selection
Abstract
The KNN algorithm with feature selection achieved the highest accuracy of 74.44% and an Area Under the Curve (AUC) of 0.8212. This model showed a balanced accuracy improvement compared to its performance using the dataset with complete features, which had an accuracy of 72.83% and an AUC of 0.8071. Similarly, the Random Forest model with feature selection showed an accuracy of 72.00% and an AUC of 0.7741, compared to an accuracy of 70.52% and an AUC of 0.7672 with all features. The SVM model with feature selection also improved, reaching an accuracy of 72.28% and an AUC of 0.7812, compared to an accuracy of 69.80% and an AUC of 0.774 with all features. Logistic Regression showed minimal change, with an accuracy of 69.14% and an AUC of 0.7644 after feature selection, compared to an accuracy of 69.25% and an AUC of 0.7645 with all features.
References
Awalina, E. F. L., & Rahayu, W. I. (2023). Optimalisasi Strategi Pemasaran dengan Segmentasi Pelanggan Menggunakan Penerapan K-Means Clustering pada Transaksi Online Retail. Jurnal Teknologi Dan Informasi, 13(2), 122–137. https://doi.org/10.34010/jati.v13i2.10090
Du, X., Yang, J., Hung, J. L., & Shelton, B. (2020). Educational data mining: a systematic review of research and emerging trends. Information Discovery and Delivery, 48(4), 225–236. https://doi.org/10.1108/IDD-09-2019-0070
Namoun, A., & Alshanqiti, A. (2021). Predicting student performance using data mining and learning analytics techniques: A systematic literature review. Applied Sciences (Switzerland), 11(1), 1–28. https://doi.org/10.3390/app11010237
Situmorang, S. (2023). Analisis Kinerja Algoritma Machine Learning Dalam Deteksi Anomali Jaringan (LAZY LEARNING. Jurnal Matematika Dan Ilmu Pengetahuan Alam, 1(4), 259–269. https://doi.org/10.59581/konstanta.v1i4.1722
Sukarna, R. H., & Ansori, Y. (2022). Implementasi Data Mining Menggunakan Metode Naive Bayes Dengan Feature Selection Untuk Prediksi Kelulusan Mahasiswa Tepat Waktu. Jurnal Ilmiah Sains Dan Teknologi, 6(1), 50–61. https://doi.org/10.47080/saintek.v6i1.1467
Tekin, A. (2014). Early Prediction of Students’ Grade Point Averages at Graduation: A Data Mining Approach. Eurasian Journal of Educational Research, 14(54), 207–226. https://doi.org/10.14689/ejer.2014.54.12
Thakar, P., Mehta, A., & Manisha. (2015). Performance analysis and prediction in educational data mining: A research travelogue. International Journal of Computer Applications, 110(15), 60–68.
Uzlah, L. I., Saputra, R. A., & Isnawaty. (2024). Deteksi Serangan Siber Pada Jaringan Komputer Menggunakan Metode Random Forest. Jurnal Mahasiswa Teknik Informatika, 8(3), 2787–2793. https://bit.ly/CyberSecurityAttacks.
Waheed, H., Hassan, S. U., Aljohani, N. R., Hardman, J., Alelyani, S., & Nawaz, R. (2020). Predicting academic performance of students from VLE big data using deep learning models. Computers in Human Behavior, 104. https://doi.org/10.1016/j.chb.2019.106189
Xing, W., Guo, R., Petakovic, E., & Goggins, S. (2015). Participation-based student final performance prediction model through interpretable Genetic Programming: Integrating learning analytics, educational data mining and theory. Computers in Human Behavior, 47, 168–181. https://doi.org/10.1016/j.chb.2014.09.034
In order to be accepted and published by Journal Agribest, author(s) submitting the article manuscript should complete all the review stages. By submitting the manuscript the author(s) agreed to these following terms:
- The copyright of received articles shall be assigned to Journal Agribest as the publisher of the journal. The intended copyright includes the right to publish articles in various forms (including reprints). Journal Agribest maintain the publishing rights to the published articles.
- Authors are permitted to disseminate published article by sharing the link/DOI of the article at Journal Agribest. authors are allowed to use their articles for any legal purposes deemed necessary without written permission from Journal Agribest with an acknowledgement of initial publication to this journal.
- Users/public use of this website will be licensed to Creative Commons Attribution 4.0 International License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.