EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Big Data enabled supply chain optimization strategies for efficient management of cross-border e-commerce goods

Zhonglin Li, Li Liu

Data and Metadata · 11.05.2026 · 5 · 805

DOI: 10.56294/dm2026805 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Data and Metadata, online erschienen am 11.05.2026. Verfasst von Zhonglin Li und 1 weiteren Autor:innen. Die Arbeit nennt 21 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

The growth of e-commerce has been very fast, particularly for cross-border activities, thus creating a great necessity for efficient services and logistics. Although the technology sector has made some progress, there is currently an evident gap that needs to be filled due to the problems of uncertainty, difficult logistics, and operational cost in the current systems.

Objective

The development of the online business has taken place at a very rapid pace, especially the cross-border business, which makes it necessary to have effective logistics services available. Even though there has been some advancement in the IT industry, still there exists a clear gap to be filled due to the issues of uncertainty, inefficiency of logistics and high operational cost involved. Method:The dataset is preprocessed using min–max normalization and missing value imputation to ensure consistency. Key attributes, including demand patterns, delivery lead times, and product categories, are extracted using PCA, reducing dimensionality and improving interpretability. The processed data is fed into an Attention-Based Convolutional Neural Network (ACNN) to model spatial and temporal relationships, while the Tangent Search Algorithm (TSA) optimizes network parameters for efficient decision-making. The ACNN-TSA hybrid is applied to optimize warehouse allocation, inventory management, and dynamic replenishment, balancing cost, delivery timeliness, and service quality. Results:Evaluation results demonstrate superior performance, constructed in Python 3,11, with MAE of 1,9543, RMSE of 1,3657, NRMSE of 0,0198, MAPE of 7,6754, and correlation (R) of 4,9325, [user2.1]highlighting improved delivery and resource utilization. Conclusion:These findings confirm a scalable and effective solution for big data-driven cross-border supply chain management.

Zitieren

APA

Li, Z., & Liu, L. (2026). Big Data enabled supply chain optimization strategies for efficient management of cross-border e-commerce goods. Data and Metadata, 5, 805. https://doi.org/10.56294/dm2026805

Vancouver

Li Z, Liu L. Big Data enabled supply chain optimization strategies for efficient management of cross-border e-commerce goods. Data and Metadata. 2026;5:805. doi:10.56294/dm2026805

BibTeX
@article{Li2026,
  author = {Li, Zhonglin and Liu, Li},
  title = {Big Data enabled supply chain optimization strategies for efficient management of cross-border e-commerce goods},
  journal = {Data and Metadata},
  year = {2026},
  volume = {5},
  pages = {805},
  doi = {10.56294/dm2026805}
}
Kostenlos starten →