Jesselyn Mu, . (2025) IMPLEMENTASI MODEL CATBOOST DAN XAI DALAM APLIKASI PREDIKSI RETENSI KARYAWAN BERBASIS STREAMLIT. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.
![[img]](http://repository.upnvj.ac.id/style/images/fileicons/text.png) |
Text
ABSTRAK.pdf Download (254kB) |
|
Text
AWAL.pdf Download (724kB) |
|
Text
BAB 1.pdf Restricted to Repository UPNVJ Only Download (322kB) |
|
Text
BAB 2.pdf Restricted to Repository UPNVJ Only Download (639kB) |
|
Text
BAB 3.pdf Restricted to Repository UPNVJ Only Download (1MB) |
|
Text
BAB 4.pdf Restricted to Repository UPNVJ Only Download (3MB) |
|
Text
BAB 5.pdf Download (294kB) |
|
Text
DAFTAR PUSTAKA.pdf Download (288kB) |
|
Text
DAFTAR RIWAYAT HIDUP.pdf Restricted to Repository UPNVJ Only Download (217kB) |
|
Text
LAMPIRAN.pdf Restricted to Repository UPNVJ Only Download (1MB) |
|
Text
HASIL PLAGIARISME.pdf Restricted to Repository staff only Download (32MB) |
|
Text
ARTIKEL KI.pdf Restricted to Repository staff only Download (935kB) |
Abstract
A company is an entity that aims to generate profit through the production of goods or services, with employees as its most valuable asset. However, employee retention has become a major challenge today, especially in Indonesia. Data shows a continuous increase in turnover from 2020 to 2024, particularly among the productive age group. Both internal and external factors influence employees' decisions to stay or resign. Therefore, this study aims to develop a Web-based application using Streamlit to predict employee retention and identify the contributing factors behind the predictions. The methodology involves the CatBoost algorithm for classification (retained or not) and regression (length of employment), as well as Explainable AI with SHAP Values for interpreting the prediction results. The findings show that the best classification model achieved an accuracy of 0.93 and an F1-score of 0.96 on the test data. The regression model achieved an R² score of 0.99 with a MAPE of 0.01, indicating excellent predictive performance. Additionally, the implementation of SHAP Values successfully identified the contributing factors in the classification predictions. The application was successfully validated through BlackBox Testing with a perfect score of 100%. This research is expected to help companies reduce turnover and retain valuable employees.
| Item Type: | Thesis (Skripsi) |
|---|---|
| Additional Information: | [No. Panggil: 2110511008] [Pembimbing 1: Neny Rosmawarni] [Pembimbing 2: Kharisma Wiati Gusti] [Penguji 1: Indra Permana Solihin] [Penguji 2: I Wayan Rangga Pinastawa] |
| Uncontrolled Keywords: | CatBoost, Explainable AI, Retention, Streamlit |
| Subjects: | Q Science > QA Mathematics > QA75 Electronic computers. Computer science Q Science > QA Mathematics > QA76 Computer software |
| Divisions: | Fakultas Ilmu Komputer > Program Studi Informatika (S1) |
| Depositing User: | JESSELYN MU |
| Date Deposited: | 12 Jul 2025 22:20 |
| Last Modified: | 17 Jul 2025 04:23 |
| URI: | http://repository.upnvj.ac.id/id/eprint/36843 |
Actions (login required)
 |
View Item |