A Stock Demand Forecasting for MSME E-Commerce Using LSTM and Facebook Prophet: A Comparative Study
DOI:
https://doi.org/10.35194/mji.v18i1.6365Keywords:
E-Commerce, Stock Forecasting, MSMEs Competitiveness, Long Short-Term Memory, Facebook prophetAbstract
Manual sales processes and stock management in micro, small, and medium enterprise (MSME) settings often lead to limited market reach and inefficient inventory management. The purpose of this research is to solve these operational problems by designing and developing a web-based e-commerce system equipped with an integrated monthly stock demand forecasting module to enhance the competitiveness of MSMEs in the roster industry. The system was developed following the waterfall methodology and it has a decoupled architecture to separate the artificial intelligence computational workloads from the core application. Two time series forecasting models Long Short-Term Memory (LSTM) and Facebook Prophet were applied and compared for forecasting stock requirements from intermittent, zero-inflated demand patterns of historical sales data. System functionality was validated using User Acceptance Testing and the forecasting accuracy was measured using Root Mean Square Error (RMSE) and Weighted Mean Absolute Percentage Error (WMAPE). The performance evaluation showed that the unscaled LSTM model outperformed the linear additive regression method of Facebook Prophet in terms of lower physical volume deviation and consistent operational error in the course of the evaluation period. The developed platform provides a reliable data-driven decision support for inventory management. The incorporation of forecasting using neural networks in the e-commerce system has reduced the risk of stockouts, expanded the market, and proved the increase in the business competitiveness of artisan MSMEs.
References
[1] S. Zhou, "E-commerce sales forecast based on neural network LSTM," in Proceedings of the 6th EAI International Conference on Computer Science and Artificial Intelligence, 2023, doi: 10.4108/eai.26-5-2023.2334251.
[2] I. G. T. Suryawan, I. K. N. Putra, P. M. Meliana, and I. G. I. Sudipa, "Performance comparison of ARIMA, LSTM, and Prophet methods in sales forecasting," Sinkron: Jurnal dan Penelitian Teknik Informatika, vol. 8, no. 4, pp. 2410–2421, 2024, doi: 10.33395/sinkron.v8i4.14057.
[3] D. Brykin, "Sales forecasting models: Comparison between ARIMA, LSTM and Prophet," Journal of Computer Science, vol. 20, no. 10, pp. 1222–1230, 2024, doi: 10.3844/jcssp.2024.1222.1230.
[4] S. Albahli, "LSTM vs. Prophet: Achieving superior accuracy in dynamic electricity demand forecasting," Energies, vol. 18, p. 278, 2025, doi: 10.3390/en18020278.
[5] N. Sunendar, H. P. Putro, and R. Hesananda, "Prediksi penjualan aerosol menggunakan algoritma ARIMA, LSTM dan GRU," Insologi: Jurnal Sains dan Teknologi, vol. 4, no. 1, pp. 113–126, 2025, doi: 10.55123/insologi.v4i1.4868.
[6] A. A. Fauziyyah, J. P. A. Brahmana, P. L. Simatupang, E. B. Soewono, and H. Hayati, "Development of a sales forecasting application using the autoregressive integrated moving average method with external input (ARIMAX)," Media Jurnal Informatika, vol. 12, no. 2, pp. 413-424, Dec. 2025, doi: 10.35194/mji.v17i2.5693.
[7] A. Saravanos and M. X. Curinga, "Simulating the software development lifecycle: The Waterfall model," Applied Systems Innovation, vol. 6, p. 108, 2023, doi: 10.3390/asi6060108.
[8] S. Saini and A. Sharma, "Impact of data preprocessing on Prophet-LSTM hybrid models for time series forecasting," Jurnal Kuey, vol. 6, no. 1, pp. 32–41, 2024. [Online]. Available: https://kuey.net/index.php/kuey/article/download/7207/5358/14154
[9] S. Gordon, J. Crager, C. Howry, A. I. Barsdorf, J. Cohen, M. Crescioni, B. Dahya, P. Delong, C. Knaus, D. S. Reasner, S. Vallow, K. Zarzar, and S. Eremenco, "Best practice recommendations: User acceptance testing for systems designed to collect clinical outcome assessment data electronically," Therapeutic Innovation & Regulatory Science, vol. 56, pp. 442–453, 2022, doi: 10.1007/s43441-021-00363-z.
[10] B. Al-Asaad, R. J. Mahmod, and M. J. Hashim, "The comparative analysis of SARIMA, Facebook Prophet, and LSTM for public-health time-series forecasting," Frontiers in Public Health, 2022, doi: 10.3389/fpubh.2022.994098.
[11] H. Patel, B. K. Bolla, S. E., and D. Reddy, "Comparative study of predicting stock index using deep learning models," arXiv preprint arXiv:2306.13931, 2023. [Online]. Available: https://arxiv.org/abs/2306.13931
[12] P. Piotrowski, I. Rutyna, D. Baczyński, and M. Kopyt, "Evaluation metrics for wind power forecasts: A comprehensive review and statistical analysis of errors," Energies, vol. 15, p. 9657, 2023, doi: 10.3390/en15249657.
[13] V. Bhaskarreddypogu and D. Prasadu, "Demand forecasting in e-commerce fashion retail: A comparative study of generative AI, LSTM and ARIMA models," Journal of Information Systems Engineering and Management, vol. 18, no. S, pp. 1–12, 2024. [Online]. Available: https://www.jisem-journal.com/
[14] A. Kumar and P. Nagpal, "Deep learning based simulation for new product demand estimation," Issues in Information Systems, vol. 25, no. 4, pp. 236–251, 2024, doi: 10.48009/4_iis_2024_119.
[15] X. Qi, K. Hou, T. Liu, Z. Yu, S. Hu, and W. Ou, "From known to unknown: Knowledge-guided transformer for time-series sales forecasting in Alibaba," arXiv preprint arXiv:2109.08381, 2021. [Online]. Available: http://arxiv.org/abs/2109.08381
[16] M. Sukel, S. Rudinac, and M. Worring, "Multimodal temporal fusion transformers are good product demand forecasters," arXiv preprint arXiv:2307.02578, 2023. [Online]. Available: http://arxiv.org/abs/2307.02578
[17] D. Arnas, H. Ariessanti, D. Aryani, and I. Sutanto, "Sistem penjualan aplikasi perancangan pada sistem penjualan aplikasi e-commerce berbasis web menggunakan metode extreme programming," ICIT Journal, vol. 11, no. 1, pp. 77–92, 2025, doi: 10.33050/icit.v11i1.3454.
[18] M. Khusnah, R. Gernowo, and B. Surarso, "Implementasi e-commerce dengan sistem informasi rekomendasi menggunakan metode collaborative filtering untuk pengembangan penjualan pada UMKM," Jurnal Sistem Informasi Bisnis, vol. 15, no. 1, pp. 134–141, 2025, doi: 10.21456/vol15iss1pp134-141.
[19] A. Widyantoro, F. F. A. Bina, T. Prayoga, R. Safei, and M. A. Arrasid, "Systematic literature review: Membandingkan pendekatan metode Agile dan Waterfall dalam pengembangan perangkat lunak," Journal of Comprehensive Science, vol. 4, no. 1, 2025
[20] T. Rahman, A. Andrean, and M. Putra, "Design and testing of e-commerce website shoe sales with Waterfall method and User Acceptance Testing (UAT)," Voteteknika, vol. 13, no. 1, 2025, doi: 10.24036/voteteknika.v13i1.133273.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Fatimatuzzahra Fatimatuzzahra, Akmal Amilunizar, Khen Dedes, Helyatin Nisyak, Nadzirotul Fitriyah
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
