EUVIMEDEUVIMED entdecken
Crossref

Multi-Level Hybrid Learning Approach for Credit Card Anomaly Detection

S. Pavithrai, N. Indhuja, C. Gopika, S.Dharshini Priya, N. Gokulapriya

International Journal of Engineering & Extended Technologies Research · 28.03.2026 · 08 (02)

DOI: 10.15662/ijeetr.2026.0802376 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Engineering & Extended Technologies Research, online erschienen am 28.03.2026. Verfasst von S. Pavithrai und 4 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Credit card fraud detection is a critical task in financial security, aiming to identify fraudulent transactions quickly and accurately to protect consumers and financial institutions. In this study, we propose a fraud detection model using the Naïve Bayes algorithm, a widely used probabilistic classifier that is efficient in handling large datasets with both categorical and continuous features. The Naïve Bayes algorithm leverages the Bayes' theorem to predict the likelihood of a transaction being fraudulent based on the features available, assuming conditional independence between the features. To address the class imbalance issue inherent fraud detection (with fraud cases being in much rarer than legitimate transactions), the model is evaluated on techniques such as data preprocessing and resampling to balance the dataset and enhance classification performance. The proposed model is tested on a credit card transaction dataset, and the results are evaluated using key metrics such as accuracy, precision, recall, F1-score, and area under the curve (AUC-ROC). Experimental findings demonstrate that the Naïve Bayes algorithm provides a robust and computationally efficient solution for fraud detection, achieving high detection rates while maintaining low computational overhead. This approach highlights the suitability of probabilistic classifiers for real-time fraud detection in financial systems, offering a reliable and scalable solution for detecting fraudulent activities in credit card transactions.

Zitieren

APA

Pavithrai, S., Indhuja, N., Gopika, C., Priya, S., & Gokulapriya, N. (2026). Multi-Level Hybrid Learning Approach for Credit Card Anomaly Detection. International Journal of Engineering & Extended Technologies Research, 08(02). https://doi.org/10.15662/ijeetr.2026.0802376

Vancouver

Pavithrai S, Indhuja N, Gopika C, Priya S, Gokulapriya N. Multi-Level Hybrid Learning Approach for Credit Card Anomaly Detection. International Journal of Engineering & Extended Technologies Research. 2026;08(02). doi:10.15662/ijeetr.2026.0802376

BibTeX
@article{Pavithrai2026,
  author = {Pavithrai, S. and Indhuja, N. and Gopika, C. and Priya, S.Dharshini and Gokulapriya, N.},
  title = {Multi-Level Hybrid Learning Approach for Credit Card Anomaly Detection},
  journal = {International Journal of Engineering & Extended Technologies Research},
  year = {2026},
  volume = {08},
  number = {02},
  doi = {10.15662/ijeetr.2026.0802376}
}
Kostenlos starten →