In the context of rapid development of e-commerce, dynamic price prediction has become a core link for enhancing enterprise competitiveness. However, existing research faces challenges such as traditional models being unable to capture nonlinear price fluctuations and insufficient real-time prediction accuracy under the influence of multiple factors in cross-border logistics, overseas warehouse location selection, and other scenarios. This study focuses on "Dynamic Price Prediction of E-commerce Based on Time Series Modeling" and uses a SARIMA-GARCH hybrid model to capture the nonlinear characteristics and heteroscedasticity of price fluctuations; Combining the Analytic Hierarchy Process (AHP) to construct an evaluation index system based on five dimensions: social, natural environment, economy, service level, and cost. The highest comprehensive score of the initial selection point 5 was selected as the overseas warehouse backup point, significantly reducing decision-making complexity; Build a dual objective optimization model that minimizes total cost and maximizes customer time satisfaction, transform it into a single objective problem through linear weighting, and use LINGO software to solve the optimal site selection plan for multiple scenarios - prioritize A1 and A5 for high satisfaction orientation, A2, A5, A6, A7 for low-cost orientation, and A1, A5, A7 for balanced weight selection. The innovation of the research lies in quantifying customer time satisfaction into site selection decisions, and linking time series models with the customer experience dimension of price prediction to enhance commercial application value. This study provides a scientific site selection decision-making framework and dynamic pricing strategy support for cross-border e-commerce enterprises, helping to improve operational efficiency and strengthen market competitiveness; In the future, it is necessary to expand the multiple influencing factors of satisfaction and explore heuristic algorithms to address the complex problems of enterprise scale expansion, and continuously optimize the adaptability of global logistics networks to dynamic market environments.

Huisheng Liu. Research on Dynamic Price Prediction of E-commerce Based on Time Series Modeling. International Journal of Business Management and Economics and Trade (2026), Vol. 7, Issue 1: 36-43. https://doi.org/10.38007/IJBMET.2026.070105.

[1] He J, Zhang N, Dynamic Price prediction Model with Transaction Costs in Short-term Portfolio Optimization. 2024 International Conference on Electronics and Devices, Computational Science (ICEDCS), 2024:198-202.

[2] Nder G T, A Comparative Analysis of Advanced Modeling Techniques for Global Methane Emission Forecasting Using SARIMA, LSTM, and GRU Models.  2024.

[3] Li W, Cai Y, Liao Z, Cross-Border E-Commerce Product Recommendation and Advanced Manufacturing Production Decisions Based on Deep Learning[C]//International Conference on AI and Financial Innovation. Springer, Singapore, 2025.

[4] Si L, "Overseas Warehouse" Make Chinese Sellers Become More "Intimate" with Overseas Buyers. China's Foreign Trade, 2024(4):47-49.

[5] Lu, Z. (2025). AI-Driven Cross-Cloud Operations Language Standardisation and Knowledge Sharing System. European Journal of AI, Computing & Informatics, 1(4), 43-50.

[6] Zhou L, Yan P, Zhang Y, et al. Using Particle Swarm Optimization with Backpropagation Neural Networks and Analytic Hierarchy Process to Optimize the Power Generation Performance of Enhanced Geothermal System (EGS). Water, 2024, 16(3):21.

[7] Kreji N, Jerinki N K, Rapaji S, et al. IPAS: An Adaptive Sample Size Method for Weighted Finite Sum Problems with Linear Equality Constraints.  2025.

[8] Irdhayanti E, Ramadhan R, Syahputri A, et al. Kreatifitas Ilmiah melalui Pelatihan Skripsi Berbasis SPSS. PaKMas: Jurnal Pengabdian Kepada Masyarakat, 2024, 4(1):116-122.

[9] Yu J, Oh D Y, Alwahaishi S, Information Disclosure in Social Network Websites: Centered on the Effect of Noncognitive Factors. Pacific Asia Journal of the Association for Information Systems, 2025, 17(3).

[10] Costa D D O, Rodrigues C M D O, Santos M, et al. SAPEVO-BSC MULTICRITERIA METHOD: A METHODOLOGICAL PROPOSAL FOR DECISION SUPPORT IN A CORPORATE SCENARIO. Anais do Simpósio Brasileiro de Pesquisa Operacional, 2024, I.

[11] Silva G, Santos A C, Genaro P, et al. Loss Function Curve to Quantify Customer (DIS) Satisfaction for Front Door Opening Entrance Height. SAE Technical Paper Series, 2024, 1.

[12] Lu, Z. (2025). Design and Practice of AI Intelligent Mentor System for DevOps Education. European Journal of Education Science, 1(3), 25-31.

[13] Yu, X. (2025). Application Analysis of User Behavior Segmentation in Enhancing Customer Lifetime Value. Journal of Humanities, Arts and Social Science, 9(10).

[14] Zheng, H. (2025). Research on Lifecycle Configuration and Reclamation Strategies for Edge Nodes Based on Microservice Architectures. Advances in Computer and Communication, 6(5).

[15] Li, J. (2025). The Impact of Distributed Data Query Optimization on Large-Scale Data Processing.