Azizah, Nurul (2026) Optimasi Pemodelan Prophet Untuk Peramalan Permintaan Produk Fast-Moving Consumer Goods (Studi Kasus: UD Aan Jaya Toko). Undergraduate thesis, Politeknik Negeri Jember.
![[img]](https://sipora.polije.ac.id/style/images/fileicons/text.png) |
Text (Abstract)
ABSTRACT.pdf - Submitted Version Available under License Creative Commons Attribution Share Alike. Download (241kB) |
|
Text (Bab 1 Pendahuluan)
BAB 1.pdf - Submitted Version Available under License Creative Commons Attribution Share Alike. Download (320kB) |
|
Text (Daftar Pustaka)
DAPUS.pdf - Submitted Version Available under License Creative Commons Attribution Share Alike. Download (218kB) |
|
Text (Laporan Lengkap)
Skripsi Pengesahann.pdf - Submitted Version Restricted to Registered users only Download (6MB) | Request a copy |
Abstract
Demand for Fast-Moving Consumer Goods (FMCG) at UD Aan Jaya Toko exhibits complex patterns, including upward trends, seasonality, demand spikes during religious holidays, and fluctuations driven by store operations and stock availability. This complexity necessitates accurate demand forecasting to support inventory optimization. This study aims to optimize the performance of the Prophet model in forecasting demand for five FMCG products (cooking oil, sugar, eggs, flour, and Sedaap Goreng instant noodles) by comparing four modeling configurations: standard model, logarithmic transformation, external regressors, and a combination of logarithmic transformation and external regressors. Modeling was optimized through hyperparameter tuning using grid search across three data split ratios (50:50, 67:33, and 83:17). The results indicate that the 83:17 data split ratio consistently yields the best performance. The external regressor configuration proved optimal for cooking oil (MAPE 7,40%), sugar (MAPE 7,88%), eggs (MAPE 7,72%), and flour (MAPE 9,00%), while the combined logarithmic transformation and external regressor model was optimal for Sedaap Goreng (MAPE 8,21%). All optimal configurations achieved MAPE values below 10% (highly accurate category). These optimal models were subsequently implemented into a web-based system using the Streamlit framework, achieving a black box testing success rate of 93,75% and a User Acceptance Testing (UAT) score of 89%
| Item Type: | Thesis (Undergraduate) | ||||||
|---|---|---|---|---|---|---|---|
| Contributors: |
|
||||||
| Uncontrolled Keywords: | peramalanpermintaan,FMCG,prophet,transformasilogaritmik, regresoreksternal,hyperparametertuning,streamlit | ||||||
| Subjects: | 410 - Rumpun Ilmu Teknik > 450 - Teknik Elektro dan Informatika > 458 - Teknik Informatika 410 - Rumpun Ilmu Teknik > 450 - Teknik Elektro dan Informatika > 461 - Sistem Informasi 410 - Rumpun Ilmu Teknik > 450 - Teknik Elektro dan Informatika > 462 - Teknologi Informasi 550 - Rumpun Ilmu Ekonomi > 570 - Ilmu Manajemen > 577 - Manajemen Informatika |
||||||
| Divisions: | Jurusan Teknologi Informasi > Prodi D4 Teknik Informatika > Tugas Akhir | ||||||
| Depositing User: | Nurul Azizah | ||||||
| Date Deposited: | 13 Oct 2026 07:57 | ||||||
| Last Modified: | 13 Oct 2026 07:58 | ||||||
| URI: | https://sipora.polije.ac.id/id/eprint/60745 |
Actions (login required)
 |
View Item |
