ACCURACY COMPARISON OF MOVING AVERAGE AND WEIGHTED MOVING AVERAGE METHODS FOR SALES FORECASTING
DOI:
https://doi.org/10.54314/e12m6433Keywords:
forecasting, moving average, sales prediction, SMA, WMAAbstract
Abstract: Sales forecasting supports production and raw-material planning in culinary businesses, yet small outlets often lack the long, multi-variable records that machine-learning models require. This study compares two simple and transparent methods, the 3-month Simple Moving Average (SMA) and Weighted Moving Average (WMA, weights 1-2-3), using monthly sales of ten burger products at Shizuka Burger Tower from January to December 2025. Accuracy was evaluated with the Mean Absolute Deviation (MAD), Mean Squared Error (MSE), and Mean Absolute Percentage Error (MAPE) over nine test months per product. Both methods were highly accurate, with MAPE below 10% for every product. The average MAPE was 3.46% for WMA and 3.58% for SMA, and WMA was more accurate for seven of the ten products, whereas SMA was better for Double Nugget, Single Patty, and Beef Patty. The advantage of WMA is therefore small and depends on the sales pattern: it appears for steadily growing products but not for products that fluctuate around a level. The results are compared with eight previous studies, and forecasts for January 2026 are reported. WMA is recommended as the default method for the outlet, with SMA as an alternative for irregular products.
Keyword: forecasting; moving average; sales prediction; SMA; WMA
Abstrak: Peramalan penjualan membantu perencanaan produksi dan bahan baku pada usaha kuliner, tetapi usaha kecil sering tidak memiliki data yang panjang dan multivariabel seperti yang dibutuhkan model pembelajaran mesin. Penelitian ini membandingkan dua metode sederhana, yaitu Simple Moving Average (SMA) 3 bulan dan Weighted Moving Average (WMA, bobot 1-2-3), menggunakan data penjualan bulanan sepuluh produk burger pada Shizuka Burger Tower dari Januari hingga Desember 2025. Akurasi dievaluasi dengan Mean Absolute Deviation (MAD), Mean Squared Error (MSE), dan Mean Absolute Percentage Error (MAPE) pada sembilan bulan pengujian untuk setiap produk. Kedua metode sangat akurat, dengan MAPE di bawah 10% untuk semua produk. Rata-rata MAPE sebesar 3,46% untuk WMA dan 3,58% untuk SMA, dan WMA lebih akurat pada tujuh dari sepuluh produk, sedangkan SMA lebih baik pada Double Nugget, Single Patty, dan Beef Patty. Keunggulan WMA dengan demikian kecil dan bergantung pada pola penjualan: tampak pada produk yang meningkat secara bertahap, tetapi tidak pada produk yang berfluktuasi di sekitar suatu level. Hasil dibandingkan dengan delapan penelitian terdahulu dan peramalan Januari 2026 dilaporkan. WMA direkomendasikan sebagai metode utama bagi usaha tersebut, dengan SMA sebagai alternatif untuk produk yang tidak beraturan.
Kata kunci: forecasting; moving average; prediksi penjualan; SMA; WMA
References
Eglite, L., & Birzniece, I. (2022). Retail sales forecasting using deep learning: Systematic literature review. Complex Systems Informatics and Modeling Quarterly, (30), 53–62. https://doi.org/10.7250/csimq.2022-30.03
Febrianti, I., Hambali, H., & Sena, M. D. (2025). Food stock analysis with the utilization of the single moving average method. Indonesian Journal of Artificial Intelligence and Data Mining, 8(2), 318–325. https://doi.org/10.24014/ijaidm.v8i2.36134
Jayamma, M., Hussain, R. A., Kumar, P. H., Kumar, M. A., Prasanth, A., & Prasharshavaradhan, S. (2025). Food demand forecasting using machine learning. Proceedings of the 1st International Conference on Research and Development in Information, Communication, and Computing Technologies (ICRDICCT 2025), 565–569. SCITEPRESS. https://doi.org/10.5220/0013886500004919
Juarsa, R. P., Kurniawan, M. A., Johan, V. S., Ismi, A. T. S., Shaura, D. N., Ritonga, M. A., & Feodora, S. (2026). Analisis peramalan penjualan pada UMKM roti gembong Aradia dengan pendekatan time series: Penggunaan metode moving average dan exponential smoothing. Industrial Engineering Journal, 15(1), 41–49. https://doi.org/10.29103/iej.v15i1.26314
Makridakis, S., Spiliotis, E., & Assimakopoulos, V. (2022). M5 accuracy competition: Results, findings, and conclusions. International Journal of Forecasting, 38(4), 1346–1364. https://doi.org/10.1016/j.ijforecast.2021.11.013
Novanda, D., & Hidayati, R. (2024). Prediction of the number of pulmonary tuberculosis disease using the moving average forecasting method and time series decomposition. Antivirus: Jurnal Ilmiah Teknik Informatika, 18(1), 37–45. https://doi.org/10.35457/antivirus.v18i1.3468
Olivos, M., Motta, A., & Castaneda, P. (2025). Optimization of food inputs in restaurants in Metropolitan Lima through prediction and monitoring based on machine learning. Proceedings of the 15th International Conference on Cloud Computing and Services Science (CLOSER 2025), 144–150. SCITEPRESS. https://doi.org/10.5220/0013233700003950
Petropoulos, F., et al. (2022). Forecasting: Theory and practice. International Journal of Forecasting, 38(3), 705–871. https://doi.org/10.1016/j.ijforecast.2021.11.001
Ramdani, I. N., & Nawindah. (2025). Comparison of single exponential smoothing and simple moving average algorithms in sales coffee forecasting. Jurnal Ilmiah Teknologi Informasi Terapan, 11(2). https://doi.org/10.33197/jitter.vol11.iss2.2025.2431
Riandi, M. H., Wiyani, N. T., & Arigawati, D. (2024). Prediksi penjualan melalui metode weighted moving average (WMA) pada UMKM “Nasi Bakar”. Jurnal Riset Entrepreneurship, 7(2), 190–205. https://doi.org/10.30587/jre.v7i2.8459
Robby, M. A. F., & Santi, R. C. N. (2022). Implementasi metode WMA, SMA, dan DES dalam menentukan jumlah stok. Elkom: Jurnal Elektronika dan Komputer, 15(2), 310–318. https://doi.org/10.51903/elkom.v15i2.743
Swaminathan, K., & Venkitasubramony, R. (2024). Demand forecasting for fashion products: A systematic review. International Journal of Forecasting, 40(1), 247–267. https://doi.org/10.1016/j.ijforecast.2023.02.005
Tako, M. A., & Ilmananda, A. S. (2026). Perbandingan metode simple moving average dan weighted moving average dalam meramalkan penjualan pada Toko El-Shaddai. Journal of Information System and Application Development, 4(1), 180–187. https://doi.org/10.26905/jisad.v4i1.16944
Wiyanti, S., Safitri, D. N., Fitri, E. S., Hidayah, R. N., & Az Zahra, E. N. (2026). Analisis peramalan penjualan telur asin menggunakan metode simple moving average sebagai dasar perencanaan produksi pada UMKM Wahyu Saputra. Journal of Development Economics and Digitalization, Tourism Economics, 3(3), 154–169. https://doi.org/10.70248/jdedte.v3i3.4161
Wulan, N. C., & Riani, L. P. (2024). Perbandingan pendekatan metode peramalan naive approach, simple moving average dan weighted moving average dalam upaya meningkatkan prediksi penjualan JNE Kopma UNY. JATI UNIK: Jurnal Ilmiah Teknik dan Manajemen Industri, 7(2), 149–160. https://doi.org/10.30737/jatiunik.v7i2.5495
Xhabafti, M., & Sinaj, V. (2025). Hybrid forecasting methods across varied domains: A systematic review. IAES International Journal of Artificial Intelligence, 14(4), 2601–2612. https://doi.org/10.11591/ijai.v14.i4.pp2601-2612
Zevender, P. S., Muziburrohman, M., Tania, T., & Rohmawati, L. (2026). Peran UMKM dalam mendorong pertumbuhan ekonomi Indonesia. Jurnal Kolaboratif Sains, 9(5), 4161–4167. https://doi.org/10.56338/jks.v9i5.11822
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Intan Saphira, Nayla Artika Dwi Kesya, Olivia Agatha Napitupulu, Putra Pratama, Raffi Ahmadinezad, Febby Madonna Yuma
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
