EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Machine Learning for Fraud Detection in E-commerce Transactions

Dr. John Smith,

American Journal of Machine Learning · 31.10.2024 · 5 (5) · 1-12

DOI: 10.71465/ajml3054 ↗

Kurz gefasst

Fachartikel in der Zeitschrift American Journal of Machine Learning, online erschienen am 31.10.2024. Verfasst von Dr. John Smith,. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Fraudulent activities in e-commerce have grown substantially, with significant losses to both businesses and consumers. Traditional fraud detection methods are often reactive and insufficient to detect complex and sophisticated fraudulent behaviors. This article explores the application of machine learning (ML) algorithms in detecting fraud in e-commerce transactions. It highlights various approaches, including supervised, unsupervised, and semi-supervised learning, to enhance fraud detection models. Furthermore, the paper evaluates the effectiveness of different ML techniques in identifying patterns in transaction data, focusing on their ability to adapt to evolving fraud strategies. The study also presents a case study of real-world implementation in an e-commerce setting, demonstrating the potential of machine learning to significantly reduce fraudulent activities.

Zitieren

APA

Smith,, D. J. (2024). Machine Learning for Fraud Detection in E-commerce Transactions. American Journal of Machine Learning, 5(5), 1-12. https://doi.org/10.71465/ajml3054

Vancouver

Smith, DJ. Machine Learning for Fraud Detection in E-commerce Transactions. American Journal of Machine Learning. 2024;5(5):1-12. doi:10.71465/ajml3054

BibTeX
@article{Smith2024,
  author = {Smith,, Dr. John},
  title = {Machine Learning for Fraud Detection in E-commerce Transactions},
  journal = {American Journal of Machine Learning},
  year = {2024},
  volume = {5},
  number = {5},
  pages = {1--12},
  doi = {10.71465/ajml3054}
}
Kostenlos starten →