Demand Forecasting UMKM Kopi Keliling Berbasis Deep Learning Klasik
DOI:
https://doi.org/10.55606/jumbiku.v5i3.6779Keywords:
Demand Forecasting, MSMEs, Deep Learning, Long Short Term Memory, ARIMA.Abstract
Mobile coffee MSMEs are part of the creative economy sector that is rapidly growing in urban areas. However, these businesses face uncertainty in daily demand, which is influenced by time, weather, location, and consumer trends. Accurate demand prediction is required to optimize inventory management, reduce the risk of losses, and increase profitability. This study aims to apply a classical deep learning approach, namely Long Short-Term Memory (LSTM), to predict the daily demand of mobile coffee MSMEs. The research data includes daily sales over 18 months with external variables such as weather, weekdays/holidays, and location. The research results indicate that the LSTM model is able to capture seasonal patterns and trends better than classical methods (ARIMA), with higher accuracy for the 7-14 days prediction horizon. These findings support data-driven decision-making for MSME actors in managing inventory, determining strategic sales locations, and designing effective promotions.
Downloads
References
Angraini, Y., Adiselcha, R. S., Nawawi, N. I. N., Izzati, N. D., Najmuddin, M. T., Rabbani, N. A., & Pangelstika, A. P. (2025). Comparativel Analysis of ARIMA and LSTM Melthods for Sela Surfacel Telmpelraturel Forelcasting in thel Sunda Strait. Jurnal Matelmatika, Statistika Dan Komputasi, 21(3), 868–885.
Badan Pusat Statistik. (2024). Statistik Pelnyeldiaan Makanan dan Minuman 2023 (2024th eld., Vol. 7). Badan Pusat Statistik.
Januschowski, T., Gasthaus, J., Wang, Y., Salinas, D., Flunkelrt, V., Bohlkel-Schnelidelr, M., & Callot, L. (2020). Critelria for classifying forelcasting melthods. Intelrnational Journal of Forelcasting, 36(1), 167–177.
Mualifah, L. N. A., Husna, D., Yasmin, J., Belrbina, A. C., Yumna, F., Uraidly, M. A., & Pangelstika, A. P. (2025). PELRBANDINGAN PELRFORMA MODELL ARIMA-GARCH DAN LSTM DALAM MELRAMALKAN JUMLAH KUNJUNGAN WISATAWAN DANAU KASTOBA. Jurnal Gaussian, 14(2), 314–324.
Muthiah, H., & Hamidah, N. K. (2025). Intelgrasi Machinel Lelarning untuk Optimalisasi Preldiksi Pelrmintaan Produk pada UMKM Kulinelr. Jurnal PelnKoMi: Kajian Pelndidikan Dan ELkonomi, 8(1), 229–233.
Muthiah, H., Hamidah, N. K., & Aryani, F. (2025). STRATELGI PELNINGKATAN ELKONOMI KRELATIF MELLALUI PRELDIKSI PELRMINTAAN PRODUK UMKM KELRAJINAN. Jurnal PelnKoMi: Kajian Pelndidikan Dan ELkonomi, 8(2), 345–348.
Nurhakiki, J., & Yahfizham, Y. (2024). Studi Kelpustakaan: Pelngelnalan 4 Algoritma Pada Pelmbellajaran Delelp Lelarning Belselrta Implikasinya. Pelndelkar: Jurnal Pelndidikan Belrkaraktelr, 2(1), 270–281.
Pahlelvi, EL. S. M. (2024). Kelcelrdasan Buatan delngan Delelp Lelarning. ELlelx Meldia Komputindo.
Pandji, B. Y., Indwiarti, I., & Rohmawati, A. A. (2019). Pelrbandingan Preldiksi Harga Saham delngan modell ARIMA dan Artificial Nelural Neltwork. Indonelsian Journal on Computing (Indo-JC), 4(2), 189–198.
Rachman, R. (2018). Pelnelrapan meltodel moving avelragel dan elxponelntial smoothing pada pelramalan produksi industri garmelnt. Jurnal Informatika, 5(2), 211–220.
Rahmita, F., Purwaningsih, S., Sari, W. G., Rawati, M., & ELffelndy, Y. (2023). Telori Pelrmintaan (Delmand) dan Subsitusi ELfelk Dalam ELkonomi Islam. Jurnal Riselt Rumpun Ilmu ELkonomi, 2(1), 246–258.
Tarumingkelng, R. C. (2024a). DELELP LELARNING.
Tarumingkelng, R. C. (2024b). DELELP LELARNING.
Yudistira, N., Alfiansih, L. M. D., Andriyani, N. I., ELssayelm, W., Nurdian, I. W., Maghfiroh, N. A., & Maulida, N. (2023). Preldiksi Delrelt Waktu Melnggunakan Delelp Lelarning. Univelrsitas Brawijaya Press.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Jurnal Manajemen, Bisnis dan Kewirausahaan
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
