Prediksi Permintaan Sewa Mobil Menggunakan Metode Triple Exponential Smoothing Berbasis Website Di Cv Mitra Sempurna Jaya

Permadani, Nensyah (2026) Prediksi Permintaan Sewa Mobil Menggunakan Metode Triple Exponential Smoothing Berbasis Website Di Cv Mitra Sempurna Jaya. Undergraduate thesis, Politeknik Negeri Jember.

	Text (Ringkasan) RINGKASAN.pdf - Submitted Version Available under License Creative Commons Attribution Share Alike. Download (98kB)
	Text (Bab 1 Pendahuluan) BAB 1 PENDAHULUAN.pdf - Submitted Version Available under License Creative Commons Attribution Share Alike. Download (134kB)
	Text (Daftar Pustaka) DAFTAR PUSTAKA.pdf - Submitted Version Available under License Creative Commons Attribution Share Alike. Download (93kB)
	Text (Laporan Lengkap) LAPORAN LENGKAP.pdf - Submitted Version Restricted to Registered users only Download (3MB) | Request a copy

Abstract

CV Mitra Sempurna Jaya is a car rental company based in Sidoarjo Regency that has been operating since 2018, managing a total fleet of 24 units including Avanza, Ertiga, Xenia, and Innova models. Throughout its operations, the company has faced challenges in planning unit availability due to a continued reliance on manual management experience. Consequently, management often struggles to predict significant surges in demand during crucial periods, such as religious holidays, New Year, and school vacation seasons. To address these issues, a web-based car rental demand prediction system was developed. This system implements the Triple Exponential Smoothing (TES) Holt-Winters Additive method as the primary algorithm, utilizing the Simple Moving Average (SMA) method as a comparative instrument. The system was built using the Laravel framework and MySQL database, supported by the Python Statsmodels library to ensure automatic optimization of model parameters. The forecasting foundation was established by processing 27 months of historical rental transaction data, spanning from January 2023 to March 2025. Evaluation results demonstrate that the TES method performs significantly better and more accurately than the SMA method across all vehicle types. This is reflected in the generated MAPE values: 5.34% for Avanza, 3.62% for Xenia, 4.51% for Ertiga, and 5.20% for Innova. As all values remain below the 10% threshold, the system's accuracy is classified as "Excellent." Furthermore, a MASE value below 1 reinforces evidence that this model is more reliable than the naive method. The system's functional quality was also tested using Function Point Analysis (FPA), achieving a score of 85.18%, indicating that the system is ready for use with high-quality standards. With this system, the management of CV Mitra Sempurna Jaya now possesses a digital tool capable of providing more accurate, efficient, and objective fleet planning recommendations based on existing historical data trends.

Actions (login required)

View Item