Model Prediksi dengan Pembelajaran Mesin dalam Pemberian Program Beasiswa kepada Calon Mahasiswa Baru Program S1 di Perguruan Tinggi Swasta.
DOI:
https://doi.org/10.26593/jrsi.v12i2.6595.187-200Kata Kunci:
pembelajaran mesin, program beasiswa, perguruan tinggi swasta, model prediksiAbstrak
Persaingan di dalam dunia pendidikan tinggi secara khusus Perguruan Tinggi Swasta (PTS) terutama di era digital menjadi semakin ketat. Dalam memperebutkan jumlah calon mahasiswa baru yang tersedia, berbagai cara dilakukan agar target penerimaan jumlah mahasiswa baru dapat tercapai. Pemberian program beasiswa adalah salah satu cara menjaring calon mahasiswa baru. Pemberian program beasiswa harus mempertimbangkan berbagai kemungkinan seperti keseriusan atau komitmen sedangkan penolakan pemberian program beasiswa dapat juga terjadi dan menjadi kendala pada akhir suatu periode Penerimaan Mahasiswa Baru (PMB). Model prediksi melalui pembelajaran mesin dengan beberapa atribut seperti asal sekolah SMA, “Kategori Sekolah” SMA, provinsi atau daerah asal SMA, jurusan saat SMA yang diambil, nilai akademik SMA, jenis pekerjaan orang tua, dan pilihan program studi atau jurusan yang akan diambil saat nanti berkuliah pada akhirnya dapat memberikan suatu indikator nilai peluang atau kemungkinan penerimaan atau penolakan program beasiswa dari seorang calon mahasiswa baru. Saat ini belum ada usaha untuk memprediksi secara sistematis terhadap penerimaan / penolakan program beasiswa. Tujuan penelitian ini adalah membangun dan membandingkan model pembelajaran mesin seperti Logistic Regression, Artificial Neural Network, Support Vector Machine, Decision Tree, Naïve Bayes, dan K Nearest Neighbors sehingga didapatkan satu model pembelajaran mesin yang memiliki prediksi yang terbaik terhadap pemberian program beasiswa. Dari hasil penelitian maka model Logistic Regression memiliki nilai akurasi rata-rata tertinggi (62,05%) saat melakukan pembelajaran model dengan data latihan dibandingkan dengan model lainnya. Akurasi model Logistic Regression memiliki nilai tertinggi terhadap data uji sebesar (62,29%) dan juga memiliki nilai AUC (0.818) yang berarti bahwa model dapat melakukan pengklasifikasian dengan baik terhadap kelompok pengambilan keputusan dibandingkan dengan model lainnya.
Referensi
Aggarwal, C.C. (2015), Data Classification Algorithms and Applications, CRC Press Taylor & Francis Group, Watson Research Center Yorktown Heights, New York, USA.
Ahmed, D.M., Abdulazeez, A.M., Zeebaree, D.Q., dan Ahmed, F.Y.H., (2021), Predicting University's Students Performance Based on Machine Learning Techniques, IEEE International Conference on Automatic Control and Intelligent Systems (I2CACIS 2021), Malaysia, June 26.
Alaka, B.O., (2017). A Dimensional student enrollment prediction model: case of Strathmore University, Master Degree Thesis, Strathmore University.
Aulck, L., Nambi, D., dan West, J., (2020), Increasing Enrollment by Optimizing Scholarship Allocations Using Machine Learning and Genetic Algorithms, Proceedings of The 13th International Conference on Educational Data Mining (EDM 2020).
Basheer, M.Y.I., Mutalib, S., Hamid, N.H.A., Rahman, S.A., dan Malik, A., (2019). Predictive analytics of university student intake using supervised methods, IAES International Journal of Artificial Intelligence (IJ-AI) Vol. 8, No. 4, December 2019, pp. 367~374.
Berens, J., Schneider, K., Görtz, S., Oster, S., dan Burghoff, J., (2019), Early Detection of Students at Risk - Predicting Student Dropouts Using Administrative Student Data from German Universities and Machine Learning Methods, Journal of Educational Data Mining, Vol. 11, No. 3.
Cardona, T.A., dan Cudney, E.A., (2019). Predicting Student Retention Using Support Vector Machines, 25th International Conference on Production Research Manufacturing Innovation: Cyber Physical Manufacturing August 9-14, 2019, Chicago, Illinois (USA).
Chawla, N.V., Bowyer, K.W., Hall, L.O., dan Kegelmeyer, W.P., (2002), “SMOTE: synthetic minority over-sampling technique,” Journal of artificial intelligence research, 321-357, 2002.
Delima, A.J.P. , (2019). Predicting Scholarship Grants Using Data Mining Techniques, International Journal of Machine Learning and Computing, Vol.9, No.4.
Fernandes, E., Holanda M., Marcio Victorinom M., Borges, V., Carvalho, R., dan Erven, G., (2018). Educational data mining: Predictive analysis of academic performance of public school students in the capital of Brazil, Elsevier Journal of Business Research
Gorunescu, F. (2011). “Data Mining : Concepts, Models and Techniques”, Springer-Verlag Berlin Heidelberg
Hamers, Y., (2017). Predicting student enrollment Logistic regression on attended marketing events, Master Degree Thesis, Tilburg University.
Han, J., Kamber, M., dan Pei, J., (2015), Data Mining Concepts and Techniques. 3rd ed. The Morgan Kaufmann series in data management systems.
Harani, N.H., dan Prianto, C., (2020). Penerapan algoritma Adaboost guna menentukan pola masuknya calon mahasiswa. Journal Transformtika, Vol.18, No.1, July 2020, pp. 123 – 132
Herlina, N. (2021).”Ditjen Diktiristek Akselerasi Program Penggabungan atau Penyatuan PTS”. (https://dikti.kemdikbud.go.id/kabar-dikti/kabar/ditjen-diktiristek-akselerasi-program-penggabungan-atau-penyatuan-pts, diakses 15 Oktober 2022).
Hosmer, D.W., Lemeshow, S., dan Sturdivant, R.X. (2013), Applied Logistic Regression. 3rd ed. John Wiley & Sons, Inc., Hoboken, New Jersey
Indrawati, A., Subagyo, H., Sihombing, A., dan Afandi, S. (2020), Analyzing The Impact Of Resampling Methode For Imbalanced Data Text In Indonesian Scientific Articles Categorization, BACA: Jurnal Dokumentasi Dan Informasi, baca.v41i2.563
Kanadpriya, B., Treena, B., Buckmire, R., dan Nishu, L., (2019), Predictive Models of Student College Commitment Decisions Using Machine Learning, MDPI Journal Data. 2019, 4, 65.
Kovacic, Z.J., (2010). Predicting student success by mining enrolment data, Proceedings of Informing Science & IT Education Conference (InSITE), 19-24 June 2010, Cassino, Italy.
Nakhkob, B., dan Khadem, M., (2015). Predicted Increase Enrollment in Higher Education Using Neural Networks and Data Mining Techniques, Journal of Computer Research and Development.
PDDikti Kementerian Riset, Teknologi, dan Pendidikan Tinggi Republik Indonesia, (2015 ~ 2020). “Statistik Pendidikan Tinggi2015~2020”.(https://pddikti.kemdikbud.go.id, diakses Juli 2022)
Pedregosa, F., Varoquaux, G. dan Gramfort, A. (2011),”Scikit-learn: Machine Learning in Python“,(https://scikitlearn.org/stable/modules/generated/sklearn.model_selection.Grid SearchCV.html, diakses 1 Maret 2023).
Ploutz, E.C., (2018). Machine Learning Applications in Graduation Prediction at the University of Nevada, Las Vegas, Master Degree Thesis, University of Nevada.
Slim, A., Hush, D., & Ojah, T., dan Babbitt, T., (2018), Predicting Student Enrollment Based on Student and College Characteristics, Proceedings of the 11th International Conference on Educational Data Mining, July 15-18, 2018, Buffalo, NY USA
Tomasevic, N., Gvozdenovic, N., dan Vranes, S., (2019), An Overview And Comparison Of Supervised Data Mining Techniques For Student Exam Performance Prediction. Elsevier Journal.
Trusheim, D., dan Rylee, C. (2011), Predictive modeling: linking enrollment and budgeting. Planning for Higher Education, 40(1):12, 2011.
Tukur, M.A., Abubakar, L.A., dan Sayuti, O.A., (2019), “Marketing Mix and Students Enrolment in Private Universities in Kwara State Nigeria”. Makerere Journal of Higher Education.
Witten, I.H., Frank, E., Hall, M.A. (2011). Data Mining : Practical Machine Learning Tools and Techniques, 3rd ed The Morgan Kaufmann series in data management systems
Yagci, M. (2022). Educational data mining: prediction of students’ academic performance using machine learning algorithms, Springer Open Journals.
