Research on e-commerce retail demand forecasting based on multi-model fusion
DOI:
https://doi.org/10.54097/ejmtfw52Keywords:
Demand Forecasting for E-commerce Retail, GM model, ARIMA model, K-Means clustering.Abstract
With the rapid refinement of the e-commerce retail sector, accurately predicting the demand for commodities has become the key for enterprises to optimize inventory management and improve supply chain efficiency. From current research, we propose an isodimensional new interest recurring GM model, ARIMA model, and K-Means clustering multi-model fusion method for e-commerce retail demand forecasting. Firstly, the etailing statistics was cleaned and preprocessed, and the 3-sigma criterion was used to identify and eliminate outliers, and secondly, the isodimensional new information compensatory GM model and the ARIMA model were combined for preliminary prediction, and the key features were extracted by K-means clustering analysis. The findings indicate that the model can accurately and robustly predict the demand in e - commerce retail. It shows high prediction precision and stability. The model developed in this study is able to offer technical assistance for the demand forecasting within the e - commerce retail domain.
Downloads
References
[1] Klein J F, Stead S, Salge O T, et al. Forecasting the future of smart hospitals: findings from a real-time delphi study. [J]. BMC health services research, 2024, 24 (1): 1421.
[2] Savas S ,Mehmet A .Marine propeller underwater radiated noise prediction with the FWH acoustic analogy part 3: Assessment of full-scale propeller hydroacoustic performance versus sea trial statistics[J].Ocean Engineering, 2022, 266 (P2).
[3] Dudukcu V H, Taskiran M, Kahraman N. UAV instantaneous power consumption prediction using LR‐TCN with simple moving average [J]. Concurrency and Computation: Practice and Experience, 2023, 36 (3).
[4] Örkényi L. A New Method for an Objective Measurement of the Judicial Workload–the Application of a Prediction Model Based on an Algorithm Formed by Multiple Linear Regression in Court Administration [J]. International Journal for Court Administration, 2022, 13 (1): 2-2.
[5] Chen X, Singh M M, Geyer P. Utilizing domain knowledge: Robust machine learning for building energy performance prediction with small, inconsistent statisticssets [J]. Knowledge-Based Systems, 2024, 294111774.
[6] M C E, J S M, J R W, et al. Unsupervised machine learning methods and emerging applications in healthcare. [J]. Knee surgery, sports traumatology, arthroscopy: official journal of the ESSKA, 2022, 31 (2): 376-381.
[7] Liu X, Salem S, Bian L, et al. Application of machine learning algorithms in the domain of financial engineering [J]. Alexandria Engineering Journal, 2024, 9594-100.
[8] Sharma V, Ghosh S, Mishra N V, et al. Spatio-temporal Variations and Forecast of PM2.5 concentration around selected Satellite Cities of Delhi, India using ARIMA model [J]. Physics and Chemistry of the Earth, 2025, 138103849-103849.
[9] Thao P P, Huong T T L. Unveiling key determinants of higher education expenditure in Vietnam: an adaptive LASSO approach in Tobit regression analysis [J]. Journal of Applied Research in Higher Education, 2025, 17 (2): 833-851.
[10] Zhao Y, Lin C, Ni A, et al. Interaction characteristics between rock burst risk region and neighboring fractural plane: a numerical investigation based on moment tensor inversion and Kmeans++ clustering [J]. Computational Particle Mechanics, 2024, (prepublish): 1-26.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Highlights in Business, Economics and Management
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
How to Cite
