Maharani, Aulia and Sutedi, Sutedi (2025) PERBANDINGAN ALGORITMA DECISION TREE, RANDOM FOREST, K-NEAREST NEIGHBOR DALAM PREDIKSI TURNOVER KARYAWAN. Skripsi thesis, Institut Informatika dan Bisnis Darmajaya.
![[img]](http://repo.darmajaya.ac.id/style/images/fileicons/text.png) |
Text
Cover.pdf Download (35kB) |
|
Text
lembar pernyataan.pdf Download (127kB) |
|
Text
Halaman Persetujuan.pdf Download (352kB) |
|
Text
Halaman Pengesahan.pdf Download (316kB) |
|
Text
Riwayat Hidup.pdf Download (228kB) |
|
Text
Halaman Persembahan.pdf Download (23kB) |
|
Text
Intisari.pdf Download (7kB) |
|
Text
Abstract (2).pdf Download (526kB) |
|
Text
Prakata.pdf Download (220kB) |
|
Text
Daftar Isi.pdf Download (137kB) |
|
Text
Daftar Tabel.pdf Download (10kB) |
|
Text
Daftar Gambar.pdf Download (8kB) |
|
Text
Bab I.pdf Download (89kB) |
|
Text
Bab II.pdf Download (233kB) |
|
Text
Bab III.pdf Download (243kB) |
|
Text
Bab IV.pdf Download (1MB) |
|
Text
Bab V.pdf Download (14kB) |
|
Text
Daftar Pusaka.pdf Download (167kB) |
Abstract
Employee turnover represents a significant challenge for companies, as it can affect operational stability and efficiency. This study compared three machine learning algorithms— Decision Tree, Random Forest, and K-Nearest Neighbor (KNN)—to predict employee turnover using a dataset consisting of 4,653 employee records. The dataset included variables such as education level, year of joining, work location, salary level, age, gender, experience in the current field, and history of unemployment. The research methodology involved data collection, data exploration, preprocessing, model implementation, and classification model evaluation. The results concluded that the Random Forest algorithm achieved the highest accuracy at 86%, followed by Decision Tree at 84%, and KNN at 79%. Therefore, Random Forest was recommended as the most effective model for predicting employee turnover due to its more stable and accurate performance. This study contributes to helping companies better understand the factors influencing employees' decisions to stay or leave, thus serving as a foundation for developing more effective employee retention strategies. Keywords: Employee Turnover, Machine Learning, Comparison
| Item Type: | Thesis (Skripsi) |
|---|---|
| Subjects: | Ilmu Komputer eSkripsi |
| Divisions: | Skripsi/TA & PKPM/KP - Fakultas Ilmu Komputer > Sistem Informasi |
| Depositing User: | Aulia Maharani |
| Date Deposited: | 10 Sep 2025 04:13 |
| Last Modified: | 10 Sep 2025 04:13 |
| URI: | http://repo.darmajaya.ac.id/id/eprint/22652 |
Actions (login required)
 |
View Item |