Prediction of Student Study Period Based on Admission Pathways Using Support Vector Machine Algorithm

Cut Maya Putri Audilla, Slamet Riyadi, Asroni Asroni

Abstract


In Indonesia, the quality of a university is measured based on the accreditation by BAN-PT (National Accreditation Board for Higher Education). BAN-PT possesses several main standards in measuring the quality of a university, one of which is students and graduates. The accuracy of the student study period is a crucial issue because it is the basis for the effectiveness of a university. Prediction is a process of systematically estimating something most likely to happen in the future based on past and present information to minimize the error (difference between something that happens and the forecast results). One technique used to make predictions is data mining. Universitas Muhammadiyah Yogyakarta (UMY), as one of the best private universities in Indonesia, must maintain the quality of its students. Student admission at UMY is an internal selection carried out through several methods: student achievement and academic ability tests. The Support Vector Machine (SVM) method is part of the prediction method. Analysis of the SVM prediction utilized the historical data from alumni of the Faculty of Law of UMY in the graduation year of 2015-2019. The application of SVM has provided better accuracy, precision, and recall results. The best kernel accuracy level was the SVM RBF kernel with an optimum C value of 10 and a gamma value of 0.4 with an accuracy of 96.00%.


Keywords


Prediction; Study Period; Student; Support Vector Machine

Full Text:

PDF

References


I. G. P. Purnaba and Dwiwahju Sasongko, BUKU III BORANG AKREDITASI “BOOK III ACCREDITATION FORM GUIDANCE.” 2017.

J. F. Ulysses, “Data Mining Classification Untuk Prediksi Lama Masa Studi Mahasiswa Berdasarkan Jalur Penerimaan Dengan Metode Naïve Bayes ‘Data Mining Classification for Predicting the Length of Student Study Period Based on the Admission Path Using the Naïve Bayes Method,’” Magister Teknik Informatika Universitas Atma Jaya Yogyakarta, 2012.

S. Guha and S. Kumar, “Emergence of big data research in operations management, information systems, and healthcare: Past contributions and future roadmap,” Production and Operations Management, vol. 27, no. 9, pp. 1724–1735, 2018.

M. S. Islam, M. M. Hasan, X. Wang, and H. D. Germack, “A systematic review on healthcare analytics: application and theoretical perspective of data mining,” in Healthcare, 2018, vol. 6, no. 2, p. 54.

H.-C. Chen et al., “Pulse-line intersection method with unboxed artificial intelligence for hesitant pulse wave classification,” Information Processing & Management, vol. 59, no. 2, p. 102855, Mar. 2022, doi: 10.1016/j.ipm.2021.102855.

K. R. Pradeep and N. C. Naveen, “Lung cancer survivability prediction based on performance using classification techniques of support vector machines, C4. 5 and Naive Bayes algorithms for healthcare analytics,” Procedia computer science, vol. 132, pp. 412–420, 2018.

M. Jupri and R. Sarno, “Taxpayer compliance classification using C4. 5, SVM, KNN, Naive Bayes and MLP,” in 2018 International Conference on Information and Communications Technology (ICOIACT), 2018, pp. 297–303.

T. Ahmad and H. Chen, “Short and medium-term forecasting of cooling and heating load demand in building environment with data-mining based approaches,” Energy and Buildings, vol. 166, pp. 460–476, 2018.

K. Meenakshi, G. Maragatham, N. Agarwal, and I. Ghosh, “A Data mining Technique for Analyzing and Predicting the success of Movie,” in Journal of Physics: Conference Series, 2018, vol. 1000, no. 1, p. 012100.

H. A. Sulistyo, T. F. Kusumasari, and E. N. Alam, “Implementation of Data Cleansing Pattern Module for Data Quality Management Application using Open Source Tools,” in 2020 3rd International Conference on Computer and Informatics Engineering (IC2IE), 2020, pp. 7–12.

A. Holzinger et al., “Interactive machine learning: experimental evidence for the human in the algorithmic loop,” Applied Intelligence, vol. 49, no. 7, pp. 2401–2414, 2019.




DOI: https://doi.org/10.18196/eist.v1i4.16598

Refbacks

  • There are currently no refbacks.


Editorial Office:

EMERGING INFORMATION SCIENCE AND TECHNOLOGY

Department of Information Technology, Faculty of Engineering,

Universitas Muhammadiyah Yogyakarta.

Jln. Brawijaya Tamantirto Kasihan Bantul 55183 Indonesia

Telp:(62)274-387656, Fax.:(62)274-387656

Website: http://journal.umy.ac.id/index.php/eist