Aplikasi Peramalan Penjualan Minuman Pada Bicopi Menggunakan Metode Double Exponential Smoothing Berbasis Android

Azzahro, Cahaya Citra (2025) Aplikasi Peramalan Penjualan Minuman Pada Bicopi Menggunakan Metode Double Exponential Smoothing Berbasis Android. Undergraduate thesis, Politeknik Negeri Jember.

	Text (Abstract) abstract.pdf - Submitted Version Available under License Creative Commons Attribution Non-commercial Share Alike. Download (250kB)
	Text (Bab 1 Pendahuluan) penda1_merge.pdf - Submitted Version Available under License Creative Commons Attribution Non-commercial Share Alike. Download (1MB)
	Text (Daftar Pustaka) dapus1_merged.pdf - Submitted Version Available under License Creative Commons Attribution Non-commercial Share Alike. Download (727kB)
	Text (Laporan Lengkap) laporan.pdf - Submitted Version Restricted to Registered users only Download (6MB) | Request a copy

Abstract

The utilization of information technology has become key to enhancing operational efficiency in the food and beverage industry. This study was conducted to address a problem identified at Bicopi Café, namely the absence of an accurate sales forecasting system, which complicates inventory planning for management. This research aims to design and build an Android-based mobile application capable of providing effective beverage sales predictions. The forecasting method employed is Double Exponential Smoothing (Holt's Method), using historical sales data from March 2023 to February 2024. The model's accuracy was evaluated using the Mean Absolute Percentage Error (MAPE) and Mean Squared Error (MSE) indicators after optimizing the Alpha (α) and Beta (β) parameters for each product. The test results indicate that the forecasting model achieved a very high level of accuracy, with the following MAPE values: Bicopi Chocolate (1.40%), Indonesia Tea (1.58%), Lychee Tea (2.28%), Long Black (4.09%), and Air Mineral (7.45%). Since all MAPE values are below 10%, the model's performance for all five products is classified as "highly accurate." These findings demonstrate that the developed application is feasible and effective for implementation as a decision-support tool at Bicopi Café, noting that each product requires a unique combination of smoothing parameters to achieve optimal accuracy.

Actions (login required)

View Item