Andika Putra Kamula, - (2022) PEMBANGUNAN MODEL KLASIFIKASI SMOTE - KNN (SYNTHETIC MINORITY OVER-SAMPLING TECHNIQUE – K-NEAREST NEIGHBOR) DALAM MEMPREDIKSI WAKTU KELULUSAN SISWA BOOTCAMP BINAR ACADEMY. S1 thesis, Universitas Pendidikan Indonesia.
![[img]](http://repository.upi.edu/style/images/fileicons/text.png) |
Text
S_KOM_1805836_Title.pdf Download (496kB) |
|
Text
S_KOM_1805836_Chapter1.pdf Download (217kB) |
|
Text
S_KOM_1805836_Chapter2.pdf Restricted to Staf Perpustakaan Download (948kB) |
|
Text
S_KOM_1805836_Chapter3.pdf Download (211kB) |
|
Text
S_KOM_1805836_Chapter4.pdf Restricted to Staf Perpustakaan Download (1MB) |
|
Text
S_KOM_1805836_Chapter5.pdf Download (77kB) |
|
Text
S_KOM_1805836_Appendix.pdf Restricted to Staf Perpustakaan Download (361kB) |
Abstract
Kelulusan tepat waktu yang rendah mempengaruhi kualitas lulusan Binar Academy, maka perlu dilakukan pemantauan oleh tim Academy Affairs (AA) terhadap perjalan bootcamp siswa. Salah satu cara adalah dengan prediksi. Educational Data Mining memiliki banyak teknik yang dapat digunakan dalam memproses data menjadi informasi, salah satunya adalah algoritma klasifikasi yaitu K-Nearest Neighboar (KNN). KNN merupakan salah satu teknik yang sering digunakan dari berbagai teknik data mining dengan salah satu alasannya yaitu mudah dipahami. Namun KNN masih memiliki beberapa kekurangan seperti kemampuan prediksi yang dipengaruhi oleh penentuan nilai K, metode penentuan jarak, serta data yang tidak seimbang. Pada penelitian yang dilakukan ini, ditemukan bahwa akurasi tertinggi 86.36% dengan K=1 menggunakan Eulidean Distanse setelah datanya dilakukan metode oversampling dengan metode SMOTE. Kata Kunci: Educational Data Mining, KNN, Prediksi, SMOTE, Binar Academy Low on-time graduation affects the quality of Binar Academy graduates. Therefor, it is necessary for the Academy Affairs (AA) team to monitor students' bootcamp journey, which one of the methods is by prediction. Educational Data Mining has many techniques that can be used to process data into information, one of which is a classification algorithm, namely K-Nearest Neighbor (KNN). KNN is one of the various data mining techniques that is often used with one reason being that it is easy to understand. However, KNN still has several shortcomings, such as the predictive capability that is influenced by the determination of the value of K, the method of determining the distance, and the unbalanced data. This study found that the highest accuracy was 86.36% with K=1 by using the Eulidean Distanse after the data was oversampled through the SMOTE method. Keywords: Educational Data Mining, KNN, Prediction, SMOTE, Binar Academy
| Item Type: | Thesis (S1) |
|---|---|
| Additional Information: | Link Google Scholar : https://scholar.google.com/schhp?hl=id |
| Uncontrolled Keywords: | Educational Data Mining, KNN, Prediksi, SMOTE, Binar Academy |
| Subjects: | L Education > L Education (General) Q Science > QA Mathematics > QA75 Electronic computers. Computer science |
| Divisions: | Fakultas Pendidikan Matematika dan Ilmu Pengetahuan Alam > Program Studi Pendidikan Ilmu Komputer |
| Depositing User: | Andika Putra Kamula |
| Date Deposited: | 05 Oct 2022 07:47 |
| Last Modified: | 05 Oct 2022 07:47 |
| URI: | http://repository.upi.edu/id/eprint/83410 |
Actions (login required)
 |
View Item |