Indriani, Sandra (2024) KOMPARASI K-NEAREST NEIGHBORS (KNN) DAN DECISION TREE DENGAN BINARY PARTICLE SWARM OPTIMIZATION (BPSO) DALAM MEMPREDIKSI KINERJA KARYAWAN. S1 thesis, Universitas Mercu Buana Jakarta-Menteng.
|
Text (Cover)
41819120071-SANDRA INDRIANI-01 Cover - Sandra Indriani.pdf Download (229kB) | Preview |
|
|
Text (Abstrak)
41819120071-SANDRA INDRIANI-02 Abstrak - Sandra Indriani.pdf Download (33kB) | Preview |
|
![[img]](https://repository.mercubuana.ac.id/style/images/fileicons/text.png) |
Text (Bab 1)
41819120071-SANDRA INDRIANI-03 Bab I - Sandra Indriani.pdf Restricted to Registered users only Download (41kB) |
|
|
Text (Bab 2)
41819120071-SANDRA INDRIANI-04 Bab II - Sandra Indriani.pdf Restricted to Registered users only Download (397kB) |
|
|
Text (Bab 3)
41819120071-SANDRA INDRIANI-05 Bab III - Sandra Indriani.pdf Restricted to Registered users only Download (148kB) |
|
|
Text (Bab 4)
41819120071-SANDRA INDRIANI-06 Bab IV - Sandra Indriani.pdf Restricted to Registered users only Download (429kB) |
|
|
Text (Bab 5)
41819120071-SANDRA INDRIANI-07 Bab V - Sandra Indriani (1).pdf Restricted to Registered users only Download (38kB) |
|
|
Text (Daftar Pustaka)
41819120071-SANDRA INDRIANI-08 Daftar Pustaka - Sandra Indriani.pdf Restricted to Registered users only Download (81kB) |
|
|
Text (Lampiran)
41819120071-SANDRA INDRIANI-09 Lampiran - Sandra Indriani (1).pdf Restricted to Registered users only Download (240kB) |
|
|
Text (Formulir Keabsahan)
41819120071-SANDRA INDRIANI-FormulirPernyataanKeabsahanDanPersetujuanPublikasiTugasAkhir - Sandra Indriani.pdf Restricted to Repository staff only Download (142kB) |
Abstract
Manajemen sumber daya manusia memiliki peran yang signifikan dalam mempengaruhi kinerja organisasi. Sebagai perusahaan yang berupaya meningkatkan objektifitas dan pengambilan keputusan yang mengandalkan data, penelitian ini berfokus untuk mengeksplorasi penerapan algoritma Machine Learning sebagai pendekatan transformatif terhadap evaluasi kinerja karyawan di PT XYZ. Ketika proses yang sudah berjalan masih menggunakan metode yang konvensional seperti sistem manual scoring, sehingga analisis yang dilakukan mungkin terbatas pada tren historis dan pemahaman intuitif yang masih sangat umum. Penelitian ini membahas tentang aspek teknis dalam implementasi algoritma Machine Learning menggunakan K-Nearest Neighbors (KNN) dan Decision Tree. Sebelum melakukan proses klasifikasi, tahap optimisasi dilakukan dengan menggunakan algoritma Binary Particle Swarm Optimization (BPSO) untuk mengetahui nilai optimal hyperparameter. Hasil dari proses klasifikasi kemudian dievaluasi menggunakan Confusion Matrix. Dataset yang digunakan pada penelitian ini memiliki 5 kelas sehingga membutuhkan pendekatan klasifikasi Multi-Class atau Multi-Class Classification (MCC). Penelitian ini menggambarkan proses penentuan hasil akhir metrik evaluasi menggunakan Confusion Matrix MCC dengan 5 kelas. Hasil akhir menunjukkan bahwa F1-Score tertinggi diperoleh dari Algoritma KNN sebesar 84.36% dan Algoritma Decision Tree sebesar 79.8%. Dengan demikian, penelitian ini memberikan kontribusi dalam merinci efektivitas penerapan algoritma Machine Learning untuk evaluasi kinerja karyawan dalam konteks organisasi PT XYZ. Human resource management has a significant role in influencing organizational performance. As a company that seeks to increase objectivity and decision making that is data driven, this research focuses on exploring the application of Machine Learning algorithms as a transformative approach to evaluating employee performance at PT XYZ. When the ongoing process still utilizes conventional methods such as manual scoring systems, the analysis conducted may be limited to historical trends and broad intuitive understanding. This research discusses technical aspects in implementing Machine Learning algorithms using K-Nearest Neighbors (KNN) and Decision Trees. Before carrying out the classification process, the optimization stage is carried out using the Binary Particle Swarm Optimization (BPSO) algorithm to determine the optimal hyperparameter values. The results of the classification process are then evaluated using the Confusion Matrix. The dataset used in this research has 5 classes so it requires a Multi-Class classification (MCC) approach. This research describes the process of determining the final results of evaluation metrics using the MCC Confusion Matrix with 5 classes. The final results show that the highest F1-Score was obtained from the KNN Algorithm at 84.36% and the Decision Tree Algorithm at 79.8%. Thus, this research contributes to maintaining the effectiveness of applying Machine Learning algorithms to evaluate employee performance in the organizational context of PT XYZ.
| Item Type: | Thesis (S1) |
|---|---|
| NIM/NIDN Creators: | 41819120071 |
| Uncontrolled Keywords: | Decision Tree, K-Nearest Neighbors (KNN), Binary Particle Swarm Optimization, Klasifikasi, Performance Review, Machine Learning, Klasifikasi Multi-Class Decision Tree, K-Nearest Neighbors (KNN), Classification, Binary Particle Swarm Optimization, Performance Review, Machine Learning Algorithm, Multi-Class Classification |
| Subjects: | 000 Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 000. Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 003 Systems/Sistem-sistem |
| Divisions: | Fakultas Ilmu Komputer > Sistem Informasi |
| Depositing User: | ANISA DESI SAFITRI |
| Date Deposited: | 24 Feb 2024 07:00 |
| Last Modified: | 24 Feb 2024 07:00 |
| URI: | http://repository.mercubuana.ac.id/id/eprint/85607 |
Actions (login required)
 |
View Item |
