EUVIMEDEUVIMED entdecken
Crossref

Product Matching using Sentence-BERT: A Deep Learning Approach to E-Commerce Product Deduplication

Heribertus Yulianton, Rina Candra Noor Santi

Engineering and Technology Journal · 31.12.2024 · 09 (12)

DOI: 10.47191/etj/v9i12.14 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Engineering and Technology Journal, online erschienen am 31.12.2024. Verfasst von Heribertus Yulianton und 1 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Product matching in e-commerce platforms presents a significant challenge due to variations in product titles, descriptions, and categorizations across different vendors. This paper presents a lightweight yet effective approach to product matching using Sentence-BERT (SBERT), specifically the all-MiniLM-L6-v2 variant. Our method combines efficient text preprocessing, strategic training pair generation, and threshold-based similarity matching to achieve high-accuracy product matching while maintaining computational efficiency. The system was evaluated on the Pricerunner dataset, achieving exceptional results with 98.10% accuracy, 100% precision, and 91.84% recall. The implementation includes a modular architecture that facilitates maintenance and updates, while the threshold-based matching strategy allows fine-tuned control over precision-recall trade-offs. Our results suggest that carefully designed preprocessing and training strategies, combined with lightweight transformer models, can achieve state-of-the-art performance in product matching without requiring complex model architectures or extensive computational resources.

Zitieren

APA

Yulianton, H., & Santi, R. C. N. (2024). Product Matching using Sentence-BERT: A Deep Learning Approach to E-Commerce Product Deduplication. Engineering and Technology Journal, 09(12). https://doi.org/10.47191/etj/v9i12.14

Vancouver

Yulianton H, Santi RCN. Product Matching using Sentence-BERT: A Deep Learning Approach to E-Commerce Product Deduplication. Engineering and Technology Journal. 2024;09(12). doi:10.47191/etj/v9i12.14

BibTeX
@article{Yulianton2024,
  author = {Yulianton, Heribertus and Santi, Rina Candra Noor},
  title = {Product Matching using Sentence-BERT: A Deep Learning Approach to E-Commerce Product Deduplication},
  journal = {Engineering and Technology Journal},
  year = {2024},
  volume = {09},
  number = {12},
  doi = {10.47191/etj/v9i12.14}
}
Kostenlos starten →