E-Commerce Demand Forecasting with ARIMA And SES Methods
DOI:
https://doi.org/10.54097/h983yv30Keywords:
Demand Forecasting, 1-wmape Indicator, RMSE, ARMIA Model, Single Exponential Smoothing.Abstract
With the rapid growth of the e-commerce industry, effective warehouse management has become essential for optimizing the supply chain. This study utilized the ARIMA model and Single Exponential Smoothing to develop a forecasting model by combining historical sales data with information on new merchandise. The model successfully predicted demand from May 16 to 30, 2024, and its accuracy was verified using the indicator. The predictions based on historical shipment data achieved an accuracy of 97.81%, while those for new dimension goods, relying on the demand for known dimension goods, reached 95.42%. These findings will significantly influence the strategic planning and operational efficiency of e-commerce companies. By optimizing inventory management, improving order processing, and enhancing supply chain collaboration, businesses can better meet consumer demand. However, the study does not provide enough focus on short-term to medium-term forecasts. Future research will aim to expand this analysis to include a long-term perspective and incorporate cross-platform data to enhance market insights.
Downloads
References
[1] Zhang, W. and X. Chen, Supply Chain Model Following Individual Demand Forecast of Online Consumers. iop conference series. earth and environmental science, 2019. 237(5): p. 52037.
[2] Guo, L., Prediction Method of Short-Term Demand for e-Commerce Goods Based on Deep Neural Network. advances in Multimedia, 2023. 2023: p. 1-14.
[3] Yin, X. and X. Tao, Prediction of seller Sales on E-Commerce Platforms Based on Data Mining and Deep Learning. scientific Programming, 2021. 2021: p . 1-9.
[4] Alghamdi, M., et al., Empowering Retail Through Advanced Consumer Product Recognition Using Aquila Optimization Algorithm With Deep Learning. iEEE Access, 2024. 12: p. 71055-71065.
[5] Song, H., D. Du and Y. Li, Research on Precise Demand Forecast of Retail Commodities Based on LSTM-ARIMA Joint Model. journal of physics. conference Journal of physics. conference series, 2021. 1865(4): p. 42049.
[6] Jiang, Xiaohong & Huimin Cao, E-commerce sales forecasting based on ARIMA model and R language implementation. Logistics Science and Technology, 2019. 42(4): pp. 52-56,69.
[7] Xiang Junkun et al, Constructing SWECPX model based on ARIMA to solve the e-commerce demand forecasting problem. China Business Journal, 2024(8): pp. 29-32.
[8] Cleger-Tamayo, S., J.M. Fernández-Luna and J.F. Huete, On the use of Weighted Mean Absolute Error in Recommender Systems. Workshop on Recommendation Utility Evaluation: Beyond RMSE (RUE 2012), held in conjunction with ACM RecSys 2012, Dublin, Ireland. 2012.
[9] Hamdanah, F.H. and D. Fitrianah, Analisis Performansi Algoritma Linear Regression dengan Generalized Linear Model untuk Prediksi Penjualan pada Usaha Mikra, Kecil, dan Menengah. Jurnal Nasional Pendidikan Teknik Informatika (JANAPATI), 2021. 10(1): p. 23-32.
[10] Ghosh, I., Tasissa, A., & Kümmerle, C. (2024). Sample-Efficient Geometry Reconstruction from Euclidean Distances using Non-Convex Optimization. advances in Neural Information Processing Systems, 37.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Highlights in Science, Engineering and Technology
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
How to Cite
