Jurnal SINTA 2
Perbandingan Algoritme Machine Learning untuk Memprediksi Pengambil Matakuliah
Jurnal Teknologi Informasi dan Ilmu Komputer (JTIIK) · Vol. 6 No. 5 (2019) · pp. 543–548
- ISSN
- 2528-6579, 2355-7699
- Published
- 2019-10-08
- Publisher
- Fakultas Ilmu Komputer, Universitas Brawijaya
- Language
- id
Abstract
Pada setiap awal semester bagian akademik melakukan penjadwalan dan penentuan matakuliah yang akan dibuka untuk semester berikutnya. Akan tetapi proses tersebut memiliki permasalahan antara lain kelas yang dibuka terlalu banyak dibanding jumlah siswa yang berminat atau sebaliknya. Selain itu, dalam permasalahan prediksi data yang terkumpul memiliki kecenderungan tidak seimbang pada setiap kelas (imbalance class). Hal ini akan berdampak pada proses penjadwalan yang kurang tepat. Sehingga dibutuhkan sistem yang dapat memprediksi mahasiswa pengambil mata kuliah. Akan tetapi ada banyak algoritme yang dapat digunakan untuk proses prediksi. Penelitian ini membandingkan performa algoritma untuk klasifikasi mahasiswa pengambil matakuliah. Pada penelitian ini prediksi dilakukan berdasarkan atribut dari data mahasiswa. Atribut-atribut tersebut yaitu Nilai, IP, IPK, SKS, SKSK dan Semester. Pada setiap observasi pada atribut-atribut tersebut prediksi akan dilakukan apakah mahasiswa tersebut mengambil mata kuliah tertentu. Prediksi dibagi menjadi 2 kelas yaitu ‘Ya’ untuk mahasiswa yang diprediksi mengambil matakuliah dan ‘Tidak’ untuk mahasiswa yang diprediksi tidak mengambil matakuliah. Teknik Synthetic Minority Oversampling Technique (SMOTE) digunakan untuk menangani data yang tidak seimbang. Pada penelitian ini klasifikasi dilakukan dengan membandingkan algoritme k-Nearest Neighbor (k-NN) dan Support Vector Machine (SVM) untuk kasus prediksi pengambil matakuliah. Hasil pengujian menggunakan 3 mata kuliah sebagai sampel. Dari hasil rerata, diperoleh hasil prediksi k-NN memiliki kinerja yang lebih baik daripada SVM. Selain itu, penggunaan teknik SMOTE dapat mempengaruhi hasil klasifikasi berupa peningkatan nilai AUC, CA, F1, precision dan recall.AbstractAt the beginning of each semester, the academic section conducts scheduling and determining the courses offered for the next semester. However, the process has problems such as too many classes offered to the student compared to the number of students who take the class or vice versa. Besides that, in the prediction problems, the collected data has an imbalance tendency in each class. As a result, these problems could cause in ineffective scheduling. Thus, there is a need to build a system that can predict students taking courses. However, there are many algorithms that can be used for the prediction. This study compares the performance of algorithms for classifications of students taking courses. In this study, predictions are modeled based on the attributes of student data, namely Grades, GPA, Cumulative GPA, Semester Credits, Cumulative Semester Credits and Semester. The classification process will be carried out to produce a prediction of whether the student takes a particular subject or not. Classification results are divided into 2 classes, namely 'Yes' for students who are predicted to take and 'No' for students who are predicted not to take the class. To handle imbalance dataset will use Synthetic Minority Oversampling Technique (SMOTE) techniques. Classification method used in this study are k-Nearest Neighbor (k-NN) and Support Vector Machine (SVM) algorithms to compare their performance for prediction cases. The test results used 3 courses as a sample. In average k-NN prediction results have a better performance than SVM. In addition, the use of SMOTE techniques can influence the classification results in the form of an increase in AUC, CA, F1, precision and recall values.
Collaboration network of the authors
40 authors · 78 co-authorship links · showing the 40 most connected
Hover or tap a name to highlight its co-authors. Double-click to open the author's page.
- University of Brawijaya
- Affiliation unknown
- Different organisations
- Same organisation
- Affiliation unknown
- Thicker line = more joint articles · bigger circle = more articles
Show as table
| Co-author | Organisation | Joint articles |
|---|---|---|
| Fajar Pradana | University of Brawijaya | 10 |
| Retno Indah Rokhmawati | University of Brawijaya | 3 |
| Satrio Hadi Wijoyo | University of Brawijaya | 3 |
| Admaja Dwi Herlambang | University of Brawijaya | 2 |
| Bayu Priyambadha | University of Brawijaya | 2 |
| Achmad Basuki | University of Brawijaya | 2 |
| Imam Cholissodin | University of Brawijaya | 2 |
| Fitri Utaminingrum | University of Brawijaya | 2 |
| Novanto Yudistira | University of Brawijaya | 2 |
| Herman Tolle | University of Brawijaya | 2 |
| Aisyah Awalina | University of Brawijaya | 2 |
| Rizal Setya Perdana | University of Brawijaya | 2 |
| Joseph Ananda Sugihdharma | University of Brawijaya | 1 |
| Nathanael Victor Darenoh | University of Brawijaya | 1 |
| Rochmat Setiyawan | University of Brawijaya | 1 |
| Budi Darma Setiyawan | University of Brawijaya | 1 |
| Ari Hernawan | University of Brawijaya | 1 |
| Aditya Rachmadi | University of Brawijaya | 1 |
| Raden Arief Setyawan | University of Brawijaya | 1 |
| Issa Arwani | University of Brawijaya | 1 |
| Aulia Akhrian Syahidi | University of Brawijaya | 1 |
| Fajerin Biabdillah | University of Brawijaya | 1 |
| Nanang Yudi Setiawan | University of Brawijaya | 1 |
| Iqbal Taufiq Ahmad Nur | University of Brawijaya | 1 |
| Bayu Sutawijaya | University of Brawijaya | 1 |
| Mochammad Dearifaldi Al Ikhsan | University of Brawijaya | 1 |
| Sulandri Sulandri | University of Brawijaya | 1 |
| Rona Salsabila | University of Brawijaya | 1 |
| Muhammad Zulfikarrahman | University of Brawijaya | 1 |
| Diva Fardiana Risa | University of Brawijaya | 1 |
| Aisyatul Maulidah | University of Brawijaya | 1 |
| Intan Yusuf Habibie | University of Brawijaya | 1 |
| Adam Syarif Hidayatullah | University of Brawijaya | 1 |
| Muhammad Wafi | University of Brawijaya | 1 |
| Ovy Rochmawanti | University of Brawijaya | 1 |
| Budi Darma Setiawan | University of Brawijaya | 1 |
| Muhammad Nugraha Delta Revanza | Affiliation unknown | 1 |
Affiliations come from OpenAlex; journal OAI-PMH metadata carries none. Authors without an OpenAlex ID are matched by name, which can merge or split people.