Analisis Prediksi Permintaan Produk FMCG menggunakan Model LSTM dan DES Untuk Optimalisasi Operasional Gudang Distribusi
Abstract
The Fast-Moving Consumer Goods (FMCG) sector is characterized by rapid product turnover and short shelf lives, requiring effective inventory management. Companies such as PT Macrosentra Niagaboga face challenges in maintaining stock availability. Although the inventory system has been integrated, stock verification is still conducted manually, requiring adaptive management to minimize the risk of overstock and stockout. Therefore, this study aims to develop a demand forecasting model using the Long Short-Term Memory (LSTM) algorithm integrated with Discrete-Event Simulation (DES) to optimize inventory management. The study utilized historical shipment data from May 2025 to January 2026. Preprocessing included data cleansing, date validation, and aggregation into daily and weekly data. Forecasting results were subsequently used as inputs for the DES simulations to determine optimal inventory policies. The results demonstrated that weekly LSTM aggregation was more accurate and stable than daily aggregation, as evidenced by a reduction in WAPE from 49.9% to 16.94% for high-demand products. Furthermore, integration with DES reduced stock levels by more than 30% using a safety stock ratio of 0.7 without compromising service levels. Finally, the proposed model was implemented in a web-based dashboard serving as a decision support system for monitoring forecasting and inventory policy recommendations.
Downloads
References
L. Isyriyah, I. Baihaqi, and F. E. Purwiantono, “Prediksi Loyalitas Pelanggan Pada Fast Moving Consumer Goods Menggunakan Klasifikasi Metode C4.5,” SMATIKA JURNAL, vol. 13, no. 02, pp. 369–380, Jan. 2024, doi: 10.32664/smatika.v13i02.1115.
R. W. Kristanto and R. R. Padmakusumah, “PENGARUH IMPLEMENTASI LEAN DAN WAREHOUSE MANAGEMENT SYSTEM TERHADAP KINERJA LOGISTIK PADA INDUSTRI FMCG PT. XYZ,” Jurnal Ilmiah Manajemen, Ekonomi, & Akuntansi (MEA), vol. 9, no. 1, pp. 547–566, 2025.
D. Irawan, E. Apriliyanto, and D. Mardiati, “Prediksi Pengiriman Teh Kemuning Di Ngargoyoso Menggunakan Algoritma Monte Carlo (Studi Kasus Pt. Rumpun Sari Kemuning),” Juti Unisi, vol. 7, no. 1, pp. 43–47, 2023.
D. Putra Romadhon and R. Eka Putra, “Penerapan Metode Deep Learning Menggunakan Algoritma CNN based Recommendation pada Aplikasi E-Commerce Gols (Studi Kasus : PT. Cipta Giri Sentosa),” Journal of Informatics and Computer Science, vol. 05, 2024.
H. Abbasimehr and M. K. Nahari, “Improving demand forecasting with LSTM by taking into account the seasonality of data,” Journal of Applied Research on Industrial Engineering, vol. 7, no. 2, pp. 177–189, 2020, doi: https://doi.org/10.22105/jarie.2020.232594.1168.
S. Salahuddin, M. Khadafi, and O. Yusrianti, “Sistem Prediksi Kebutuhan Stock Obat Menggunakan Metode Long Short Term Memory (LSTM) Time Series Berbasis Deep Learning,” in Prosiding Seminar Nasional Politeknik Negeri Lhokseumawe, 2025, pp. 26–33.
P. Anjarwati and P. Widyaningsih, “Raw Material Stock Prediction Using the Long Short-Term Memory Algorithm (Case Study: Mizan and Sunan Grilled Bread Producers),” Journal of Artificial Intelligence and Software Engineering, vol. 5, no. 3, pp. 1296–1308, 2025, doi: 10.30811/jaise.v5i3.7199.
R. A. Saputra, Y. Azhar, and V. Rahmayanti, “Prediksi Permintaan Kargo pada Cargo Service Center Tangerang City Menggunakan Metode Gated Recurrent Unit,” REPOSITOR, vol. 2, no. 8, pp. 1113–1122, 2020.
A. Ichwani, L. Wahyu, A. Saputro, G. Putra Pradana, and J. Maulindar, “Implementasi Algoritma Random Forest untuk Prediksi Permintaan dan Optimasi Stok pada Sistem Manajemen Inventori Layanan Pengiriman Makanan,” Seminar Nasional Teknologi Informasi dan Bisnis (SENATIB), p. 2025, 2025.
L. A. Anbar and W. Wahyudin, “Peramalan permintaan tas laptop menggunakan model time series,” Journal Industrial Servicess, vol. 7, no. 2, p. 285, Apr. 2022, doi: 10.36055/jiss.v7i2.14326.
J. K. Franco, N. M. Guevara, P. Castaneda, J. Mansilla-Lopez, and A. D. Garcia-Nunez, “A Machine Learning-Based Stock Forecasting Method for Inventory Optimization in Micro and Small Enterprises,” Engineering, Technology & Applied Science Research, vol. 16, no. 1, pp. 32081–32088, 2026.
M. Mazzi, L. Aboueljinane, and M. Lebbar, “Monte Carlo Simulation and Genetic Algorithm for Optimizing Hospital Medicine Inventory Management under Uncertainty,” Procedia Comput. Sci., vol. 277, pp. 3093–3102, 2026.
D. Dornela Goulart, R. de Carvalho, M. Almeida Henriques, and B. Kawany Gonçalves Nunes Carvalho, “Predictive models for inventory optimization: a machine learning application for demand forecasting at a construction supplies distributor,” Future Business Journal, vol. 12, no. 1, p. 92, 2026.
D. Susilo, A. Chusyairi, M. Ikhwani Saputra, U. Siber Asia, J. R. Harsono, and P. Minggu Jakarta Selatan, “Sistematis : Jurnal Ilmiah Sistem Informasi Prediksi Penjualan Untuk Optimasi Stock Produk Menggunakan Algoritma Long Short Term Memory,” 2025, doi: 10.69533.
E. Caro and J. Juan, “Probabilistic analysis of electricity load forecasting errors,” Electric Power Systems Research, vol. 255, Jun. 2026, doi: 10.1016/j.epsr.2026.112807.
A. González and V. Parada, “An Adaptive Model Selection Framework for Demand Forecasting under Horizon-Induced Degradation to Support Business Strategy and Operations,” arXiv preprint arXiv:2602.13939, 2026.
R. Skapinyecz, “Recent Trends in the Optimization of Logistics Systems Through Discrete-Event Simulation and Deep Learning,” Sep. 01, 2025, Multidisciplinary Digital Publishing Institute (MDPI). doi: 10.3390/a18090573.
P. Raska, Z. Ulrych, J. Baloun, M. Malaga, and L. Lenc, “USING ADAPTIVE NEURAL NETWORKS FOR OPTIMISING DISCRETE EVENT SIMULATION,” International Journal of Simulation Modelling, vol. 23, no. 2, pp. 227–238, Jun. 2024, doi: 10.2507/IJSIMM23-2-678.
E. Sherzer and Y. Barron, “Supervised Learning for the (s, S) Inventory Model with General Interarrival Demands and General Lead Times,” arXiv preprint arXiv:2601.12900, 2026.
Y. Li and Z. Wei, “Regional Logistics Demand Prediction: A Long Short-Term Memory Network Method,” Sustainability (Switzerland), vol. 14, no. 20, Oct. 2022, doi: 10.3390/su142013478.
J. Anggara, F. R. Ramadhan, A. F. Syofian, A. A. Panjaitan, and R. F. Fithra, “Pengembangan Sistem Prediksi Harga dan Rekomendasi Mobil Bekas Berbasis Machine Learning,” Journal of Technology and Informatics (JoTI), vol. 7, no. 1, pp. 11–23, Apr. 2025, doi: 10.37802/joti.v7i1.987.
R. Zaqi Megantara, P. Iryanto Faot, R. Haba Ito, K. Felicia Annabel, and O. Karnalim, “Pemanfaatan Machine Learning dalam Prediksi Rating: Studi Kasus pada Data Abstrak Publikasi Ilmiah,” Journal of Technology and Informatics (JoTI), vol. 7, no. 1, pp. 62–75, Apr. 2025, doi: 10.37802/joti.v7i1.999.
I. R. Siregar, A. Nugraha, K. A. Notodiputro, Y. Angraini, and L. N. A. Mualifah, “The comparison of long short-term memory and bidirectional long short-term memory for forecasting coal price,” BAREKENG: JURNAL ILMU MATEMATIKA DAN TERAPAN Учредители: Universitas Pattimura, vol. 19, no. 1, pp. 245–258, 2025.
E. Bottani and G. Casella, “Discrete-event simulation in logistics and supply chain management: a scientometric perspective,” Prod. Manuf. Res., vol. 12, no. 1, 2024, doi: 10.1080/21693277.2024.2415038.
M. Kholil, I. Almahdy, A. Fortinina, and A. Suparno, “Implementation of continuous review system method, periodic review system method and min-max method for cheese powder inventory (Case study: PT. Mayora Indah TBK),” International Journal of Advanced Technology in Mechanical, Mechatronics and Materials, vol. 1, no. 2, pp. 45–49, 2020.
Copyright (c) 2026 Tanti Cahya Herdiyani, Taswanda Taryo, Kahfi Heryandi Suradiradja, Zafira Salsabilah
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
