EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Evaluating machine learning models compared to traditional supplier qualification process techniques in Supply Chain Management

Laura Nogueira Cordeiro, Alberto Casado Lordsleem Junior, Thais Cohen de Almeida Costa, Emilia Rahnemay Kohlman Rabbani

Brazilian Journal of Operations & Production Management · 03.04.2026 · 23 (1) · 3022

DOI: 10.14488/bjopm.3022.2026 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Brazilian Journal of Operations & Production Management, online erschienen am 03.04.2026. Verfasst von Laura Nogueira Cordeiro und 3 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Goal: This study systematically reviews the literature on the application of machine learning algorithms in the selection, evaluation, and prediction of supplier performance in the context of supply chain management, identifying trends and opportunities for future research. Design/methodology/approach: A systematic literature review was conducted, conducted, following the PRISMA protocol. The search was conducted in Scopus, ScienceDirect, Web of Science, and Engineering Village databases, considering articles published between 2015 and 2025. After applying the inclusion and exclusion criteria, 27 studies were selected and analyzed regarding the type of learning, performance metrics, application sectors, and methodological characteristics.

Results

The results indicate a predominance of supervised models (89.7%), with emphasis on algorithms based on decision trees and neural networks. The reported accuracies range from 46% to 99%, with an overall average of 91.97%, highlighting advances in the use of data-driven models for supplier classification and ranking.

Limitations

The main limitations relate to the heterogeneity of the databases, the lack of standardization of evaluation metrics, and the incomplete methodological description in some of the analyzed studies.Practical implications: The study demonstrates that machine learning can support strategic decisions in purchasing and supply, increasing the accuracy in supplier selection and evaluation.Originality/Value: The study offers a systematic and structured synthesis of recent literature, organizing evidence by algorithmic families, performance metrics, and application sectors, in addition to identifying relevant gaps for future research.

Zitieren

APA

Cordeiro, L. N., Junior, A. C. L., Costa, T. C. D. A., & Rabbani, E. R. K. (2026). Evaluating machine learning models compared to traditional supplier qualification process techniques in Supply Chain Management. Brazilian Journal of Operations & Production Management, 23(1), 3022. https://doi.org/10.14488/bjopm.3022.2026

Vancouver

Cordeiro LN, Junior ACL, Costa TCDA, Rabbani ERK. Evaluating machine learning models compared to traditional supplier qualification process techniques in Supply Chain Management. Brazilian Journal of Operations & Production Management. 2026;23(1):3022. doi:10.14488/bjopm.3022.2026

BibTeX
@article{Cordeiro2026,
  author = {Cordeiro, Laura Nogueira and Junior, Alberto Casado Lordsleem and Costa, Thais Cohen de Almeida and Rabbani, Emilia Rahnemay Kohlman},
  title = {Evaluating machine learning models compared to traditional supplier qualification process techniques in Supply Chain Management},
  journal = {Brazilian Journal of Operations & Production Management},
  year = {2026},
  volume = {23},
  number = {1},
  pages = {3022},
  doi = {10.14488/bjopm.3022.2026}
}
Kostenlos starten →