MENINGKATKAN AKURASI PREDIKSI KELULUSAN MAHASISWA MENGGUNAKAN METODE ALGORITMA GENETIKA

Sumarna Sumarna, Imam Nawawi, Suhardjono Suhardjono, Hari Sugiarto, Dewi Yuliandari

Abstract


Penelitian ini bertujuan untuk meningkatkan akurasi prediksi kelulusan mahasiswa melalui penerapan dan optimasi algoritma Naïve Bayes (NB) menggunakan Genetic Algorithm (GA). Teknik data mining digunakan untuk menganalisis atribut akademik dan demografis mahasiswa guna mengidentifikasi pola yang dapat memprediksi kemungkinan kelulusan mahasiswa. Penelitian ini menerapkan metode kuantitatif dengan memanfaatkan dataset berisi 796 catatan mahasiswa dari sebuah institusi pendidikan tinggi di Indonesia. Proses preprocessing data dilakukan untuk menangani missing value sebelum diterapkan ke dalam algoritma. Hasil algoritma NB menujukan akurasi prediksi sebesar 83,30% dengan precision 57,91% dan recall 74,01%. Setelah dilakukan optimasi dengan GA, akurasi meningkat menjadi 85,43% dengan precision 67,10%, meskipun recall sedikit menurun menjadi 61,07%. Analisis perbandingan menunjukkan NB+GA lebih unggul dalam hal akurasi dan precision, namun algoritma NB tanpa optimasi memiliki keunggulan dalam recall yang penting untuk mendeteksi seluruh kasus positif. Ini menunjukkan bahwa integrasi GA dalam NB dapat meningkatkan beberapa aspek kinerja model, namun menimbulkan trade-off antara precision dan recall. Kombinasi NB dan GA tetap menawarkan pendekatan yang kompetitif dalam prediksi kelulusan mahasiswa. Hasil penelitian ini dapat menjadi dasar untuk pengembangan sistem pendukung keputusan di lembaga pendidikan tinggi.

Full Text:

PDF

References


Bokgoshi, L., Sixhaxa, K., Jadhav, A., Nyamane, S., & Ajoodha, R. (2023). Enhancing Timely Graduations: An Explainable AI Approach to Predict Academic Risks in South African Students. International Conference on Electrical, Computer and Energy Technologies (ICECET). IEEE. https://doi.org/10.1109/ICECET58911.2023.10389444

Gustiana, Z., & Sari, A. N. (2021). Combination of C 4.5 Algorithm and Profile Matching for Determining University Students Graduation. International Conference on Computer Science and Engineering (IC2SE). IEEE. https://doi.org/10.1109/IC2SE52832.2021.9791954

Hendra, Azis, M. A., & Suhardjono. (2020). ANALISIS PREDIKSI KELULUSAN MAHASISWA MENGGUNAKAN DECISSION TREE BERBASIS PARTICLE SWARM OPTIMIZATION. Jurnal Sisfokom (Sistem Informasi Dan Komputer), 9(1), 102–107. https://doi.org/https://doi.org/10.32736/sisfokom.v9i1.756

Islam, M. R., Banik, S., Rahman, K. N., & Rahman, M. M. (2023). A comparative approach to alleviating the prevalence of diabetes mellitus using machine learning. Computer Methods and Programs in Biomedicine, 4. https://doi.org/https://doi.org/10.1016/j.cmpbup.2023.100113

Kahfi, A. H., Prihatin, T., Yudhistira, Sudradjat, A., & Wijaya, G. (2024). THE RIGHT STEPS TOWARDS GRADUATION: NB-PSO SMART COMBINATION FOR STUDENT GRADUATION PREDICTION. Jurnal Teknik Informatika (Jutif), 5(2), 607–614. https://doi.org/https://doi.org/10.52436/1.jutif.2024.5.2.1889

Karmagatri, M., Kurnianingrum, D., Suciana, M. R., & Utami, S. A. (2023). Predicting Factors Related to Student Performance Using Decision Tree Algorithm. International Conference on Cybernetics and Intelligent System (ICORIS). IEEE. https://doi.org/10.1109/ICORIS60118.2023.10352269

Kurniawati, G., & Maulidevi, N. U. (2022). Multivariate Sequential Modelling for Student Performance and Graduation Prediction. International Conference on Information Technology, Computer, and Electrical Engineering (ICITACEE). IEEE. https://doi.org/10.1109/ICITACEE55701.2022.9923971

Laurentinus, Rizan, O., Sarwindah, Hamidah, Sulaiman, R., & Fuston, P. (2022). Data Mining Using C4.5 Algorithm in Predicting Student Graduation. International Seminar on Research of Information Technology and Intelligent Systems (ISRITI). IEEE. https://doi.org/10.1109/ISRITI56927.2022.10052793

Liao, X. (2023). Research and enlightenment on the Graduation Rate of American Universities Based on Panel Data. International Conference on Management Engineering, Software Engineering and Service Sciences (ICMSS). IEEE. https://doi.org/10.1109/ICMSS56787.2023.10118079

Lin, K. (2023). Research on Graduation Destination Prediction Algorithm Based on Students’ Learning Behavior Data. Asian Conference on Artificial Intelligence Technology (ACAIT). IEEE. https://doi.org/10.1109/ACAIT60137.2023.10528473

Nurdin, H., Sartini, Sumarna, Maulana, Y. I., & Riyanto, V. (2023). Prediction of Student Graduation with the Neural Network Method Based on Particle Swarm Optimization. Sinkron : Jurnal Dan Penelitian Teknik Informatika, 8(4), 2353–2362. https://doi.org/10.33395/sinkron.v8i4.12973

Ong, D. P., & Pedrasa, J. R. I. (2021). Student Risk Assessment: Predicting Undergraduate Student Graduation Probability Using Logistic Regression, SVM, and ANN. TENCON 2021 - 2021 IEEE Region 10 Conference (TENCON). IEEE. https://doi.org/10.1109/TENCON54134.2021.9707322

Pangesti, W. E., Ariyati, I., Priyono, Sugiono, & Suryadithia, R. (2024). Utilizing Genetic Algorithms To Enhance Student Graduation Prediction With Neural Networks. Sinkron : Jurnal Dan Penelitian Teknik Informatika, 9(1), 276–284. https://doi.org/https://doi.org/10.33395/sinkron.v9i1.13161 e-ISSN

Rawatlal, R., Chetty, M., & Naicker, A. K. (2022). Latent Factors for Consistently Predicting Student Success. World Engineering Education Forum - Global Engineering Deans Council (WEEF-GEDC). IEEE. https://doi.org/10.1109/WEEF-GEDC54384.2022.9996209

Ridwansyah, R., Wijaya, G., & Purnama, J. J. (2020). Hybrid Optimization Method Based on Genetic Algorithm for Graduates Students. Jurnal Pilar Nusa Mandiri, 16(1), 53–58.




DOI: http://dx.doi.org/10.36723/juri.v16i2.706

Refbacks

  • There are currently no refbacks.


Lisensi Creative Commons
Ciptaan disebarluaskan di bawah Lisensi Creative Commons Atribusi-NonKomersial 4.0 Internasional.

 

 

 

 

 

View My Stats