MAULANA, MUHAMMAD ADIKA (2026) PREDIKSI PELANGGARAN SLA PADA SISTEM TICKETING MENGGUNAKAN LOGISTIC REGRESSION, DECISION TREE, DAN RANDOM FOREST DI PT. INDONESIAN CLOUD. S1 thesis, Universitas Mercu Buana Jakarta.
|
Text (HAL COVER)
Cover.pdf Download (939kB) | Preview |
|
![[img]](https://repository.mercubuana.ac.id/style/images/fileicons/text.png) |
Text (BAB I)
Bab 1.pdf Restricted to Registered users only Download (33kB) |
|
|
Text (BAB II)
Bab 2.pdf Restricted to Registered users only Download (122kB) |
|
|
Text (BAB III)
Bab 3.pdf Restricted to Registered users only Download (73kB) |
|
|
Text (BAB IV)
Bab 4.pdf Restricted to Registered users only Download (101kB) |
|
|
Text (BAB V)
Bab 5.pdf Restricted to Registered users only Download (41kB) |
|
|
Text (DAFTAR PUSTAKA)
Daftar Pustaka.pdf Restricted to Registered users only Download (76kB) |
|
|
Text (LAMPIRAN)
Lampiran.pdf Restricted to Registered users only Download (236kB) |
Abstract
The performance of IT services heavily depends on the ability of the Service Desk to resolve tickets in accordance with SLA. SLA violations can lead to decreased service quality, increased backlog, and potentially lower user satisfaction. This study aims to develop a predictive model for SLA violations in the ticketing system at PT Indonesian Cloud using three classification algorithms: Logistic Regression, Decision Tree, and Random Forest. The historical ticket data used includes problem categories, priority, assignment group, response time, resolution time, and other relevant variables. The research process was conducted through stages of data cleaning, exploration, feature transformation, and modeling. The results indicate that Random Forest provides the best performance in predicting potential SLA violations, with higher accuracy and generalization capability compared to the other two models. The resulting predictive model has the potential to be used as an early warning system, enabling the operational team to take preventive actions before the SLA deadline is exceeded. The implementation of this predictive model is expected to enhance ticket resolution effectiveness and support more proactive decision-making in IT service management at PT Indonesian Cloud. Kata kunci: Ticketing System, Logistic Regression, Decision Tree, Random Forest, Service desk. Kinerja layanan TI sangat bergantung pada kemampuan Service desk dalam menyelesaikan tiket sesuai . Pelanggaran SLA dapat menyebabkan menurunnya kualitas layanan, meningkatnya backlog, serta berpotensi menurunkan kepuasan pengguna. Penelitian ini bertujuan untuk membangun model prediksi pelanggaran SLA pada sistem ticketing di PT Indonesian Cloud menggunakan tiga algoritma klasifikasi, yaitu Logistic Regression, Decision Tree, dan Random Forest. Data historis tiket yang digunakan mencakup kategori masalah, prioritas, assignment group, waktu respons, waktu penyelesaian, serta variabel lain yang relevan. Proses penelitian dilakukan melalui tahapan pembersihan data, eksplorasi, transformasi fitur, dan pemodelan. Hasil penelitian menunjukkan bahwa Random Forest memberikan performa terbaik dalam memprediksi potensi pelanggaran SLA, dengan akurasi dan kemampuan generalisasi yang lebih tinggi dibandingkan dua model lainnya. Model prediksi yang dihasilkan berpotensi digunakan sebagai sistem peringatan dini (early warning), sehingga tim operasional dapat mengambil tindakan preventif sebelum batas waktu SLA terlampaui. Implementasi model prediktif ini diharapkan dapat meningkatkan efektivitas penanganan tiket serta mendukung pengambilan keputusan yang lebih proaktif dalam pengelolaan layanan TI di PT Indonesian Cloud. Kata kunci: Ticketing System, Logistic Regression, Decision Tree, Random Forest, Service desk
Actions (login required)
 |
View Item |
