Predictive Sparepart Maintenance Menggunakan Algoritma Machine Learning Extreme Gradiant Boosting Regressor

Syahrul Usman; Rahmat Fuadi Syam

doi:10.61628/jsce.v5i2.1418

Syahrul Usman
Rahmat Fuadi Syam Universitas Pancasakti

DOI: https://doi.org/10.61628/jsce.v5i2.1418

Keywords: Predictive, Machin Learning, XGBoost Regressor, Sparepart, After Sales

Abstract

Spare parts are components that make up a single object that has a specific function. In car vehicles, spare parts have the function of maintaining the performance and function of the vehicle. Predictive Spare Part Maintenance is an effort to improve operational efficiency, customer service, and reduce vehicle downtime through the application of analysis and machine learning algorithms to predict spare part replacement times. A machine learning approach can be used to predict maintenance times for car spare parts, where one of the algorithms that can be used is XGBoost Regressor. Through this approach, this research aims to improve service planning by predicting spare part replacement times based on certain indicators, With the implementation of this research, it is hoped that it can increase operational efficiency in automotive after-sales services, increase customer satisfaction, reduce vehicle downtime, and improve overall service planning and most importantly can provide preventive maintenance information to customers. This research provides prediction results with R2-Score values as follows: train data: 93%, Valid: 90%, Test: 90%

References

Andriansyah, D.-, & Eka Wulansari Fridayanthie. (2023). Optimization of Support Vector Machine and XGBoost Methods Using Feature Selection to Improve Classification Performance. JOURNAL OF INFORMATICS AND TELECOMMUNICATION ENGINEERING, 6(2), 484–493. https://doi.org/10.31289/jite.v6i2.8373

Asohi, Y. (2020). IMPELEMENTASI ALGORITMA REGRESI LINIER BERGANDA UNTUK PREDIKSI PENJUALAN. In Jurnal Nasional Ilmu Komputer (Vol. 1, Issue 3).

Cadang, P. S., Berbasis, B., Pada Bengkel, W., Motor, D., & Nurhachita, P. (2019). Sistem Informasi.

Ovilianda, A., & Ginting, B. (2021). Penerapan Data Mining Korelasi Penjualan Spare Part Mobil Menggunakan Metode Algoritma Apriori (Studi Kasus: CV. Citra Kencana Mobil). In JOURNAL OF INFORMATION AND TECHNOLOGY UNIMOR.

Purnomo, J., Affandi, N., Rahmatullah, A., Manajemen, J., & Bina Bangsa, U. (n.d.). ANALISIS PENERAPAN PERAWATAN MOTOR KONVEYOR MESIN XRAY DENGAN MENGGUNAKAN METODE RELIABILITY CENTERED MAINTENANCE (RCM) PADA PT. TRISTAN ENGINEERING. Jurnal Ilmiah Teknik Dan Manajemen Industri Jurnal Taguchi, 1(2), 134–270. https://doi.org/10.46306/tgc.v1i2

Sampul, H., Oleh, S., Sihombing, J., Teknik, F., & Komputer, D. (2021). IMPLEMENTASI AUGMENTED REALITY SEBAGAI MEDIA PENGENALAN SPAREPART MOBIL BERBASIS ANDROID PROGRAM STUDI TEKNIK INFORMATIKA.

Sihombing, P. R., Suryadiningrat, S., Sunarjo, D. A., & Yuda, Y. P. A. C. (2023). Identifikasi Data Outlier (Pencilan) dan Kenormalan Data Pada Data Univariat serta Alternatif Penyelesaiannya. Jurnal Ekonomi Dan Statistik Indonesia, 2(3), 307–316. https://doi.org/10.11594/jesi.02.03.07

Supriana, W., Raharja, M. A., Made, I., & Bimantara, S. (n.d.). SINTECH Journal | 1 Pengembangan Sistem Prediksi Bantuan Program Keluarga Harapan (PKH) Berbasis Machine Learning. https://doi.org/10.31598

Usman, S., Aziz, F., Mipa, F., & Studi Ilmu Komputer, P. (2022). FORECASTING PENGENDALIAN PERSEDIAAN SUKU CADANG MENGGUNAKAN METODE NAIVE. In Jeffry (Vol. 8, Issue 1). Firman Aziz.

Wiki Lofandri. (2022). Analisis Predictive Maintenance Peralatan Lab Berbasis Machine Learning. Jurnal Sistim Informasi Dan Teknologi. https://doi.org/10.37034/jsisfotek.v5i1.164