EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Enhancing Personalized E-Commerce Recommendations Under the User–Agent–Platform Paradigm: An LLM-Driven Method

Junbiao Xu, Zhicai Zhang, Chong Zhang

Journal of Theoretical and Applied Electronic Commerce Research · 10.07.2026 · 21 (7) · 223

DOI: 10.3390/jtaer21070223 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Theoretical and Applied Electronic Commerce Research, online erschienen am 10.07.2026. Verfasst von Junbiao Xu und 2 weiteren Autor:innen. Die Arbeit nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Research Foundation for Youth Scholars of Beijing Technology and Business University.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Recommendation systems are widely used in e-commerce, social media, and content distribution, yet LLM-based recommendation workflows still face recurring challenges in data completeness, sample balance, and output stability. In addition, the conventional “user-platform” structure leaves limited room for user-side mediation of exposure and preference expression. This paper presents ABP, a workflow-level extension of i2Agent in the User–Agent–Platform setting. ABP contains three modules: Adaptive Description Enrichment (ADE), Batch-balanced Sampling Strategy (BSS), and Prompt-driven Workflow Optimization (PWO). ADE repairs missing or rigid item text with richer natural-language descriptions, BSS builds balanced comparative inputs for user profiling, and PWO strengthens multi-stage reasoning with structured output constraints. Experiments on four real-world datasets show that ABP achieves strong ranking results under the reported protocol. Across the 16 reported dataset–metric pairs, the five-run mean results of ABP show an average relative improvement of 24.62% over i2Agent, with especially large gains on Amazon Book and Amazon Movietv. Under a fixed five-run protocol, ABP shows limited run-to-run dispersion on Amazon Book, Amazon Movietv, and Yelp, while Goodreads exhibits comparatively larger but still bounded variation. Overall, these results suggest that carefully designed workflow improvements can improve LLM-based recommendation quality in the reported setting while maintaining the agent’s role as a user-side mediation layer in the User–Agent–Platform setting.

Förderung

  • National Natural Science Foundation of China
  • Research Foundation for Youth Scholars of Beijing Technology and Business University

Zitieren

APA

Xu, J., Zhang, Z., & Zhang, C. (2026). Enhancing Personalized E-Commerce Recommendations Under the User–Agent–Platform Paradigm: An LLM-Driven Method. Journal of Theoretical and Applied Electronic Commerce Research, 21(7), 223. https://doi.org/10.3390/jtaer21070223

Vancouver

Xu J, Zhang Z, Zhang C. Enhancing Personalized E-Commerce Recommendations Under the User–Agent–Platform Paradigm: An LLM-Driven Method. Journal of Theoretical and Applied Electronic Commerce Research. 2026;21(7):223. doi:10.3390/jtaer21070223

BibTeX
@article{Xu2026,
  author = {Xu, Junbiao and Zhang, Zhicai and Zhang, Chong},
  title = {Enhancing Personalized E-Commerce Recommendations Under the User–Agent–Platform Paradigm: An LLM-Driven Method},
  journal = {Journal of Theoretical and Applied Electronic Commerce Research},
  year = {2026},
  volume = {21},
  number = {7},
  pages = {223},
  doi = {10.3390/jtaer21070223}
}
Kostenlos starten →