محفوظ في:
| المؤلف الرئيسي: | |
|---|---|
| التنسيق: | Recurso digital |
| اللغة: | الإنجليزية |
| منشور في: |
Zenodo
2026
|
| الموضوعات: | |
| الوصول للمادة أونلاين: | https://doi.org/10.5281/zenodo.20050659 |
| الوسوم: |
إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
|
جدول المحتويات:
- <p class="MsoNormal"><em><span>The rapid growth of digital payment platforms has significantly increased the risk of fraudulent transactions, making effective fraud detection a critical concern for financial institutions. This paper presents an Online Payment Fraud Detection System utilizing Artificial Neural Networks (ANN) — a deep learning-based web application that enables end-to-end automation of fraud classification. The system accepts transaction datasets, automatically performs preprocessing including feature normalization and label encoding, splits data into training and test sets, and trains a multi-layer ANN model optimized for binary fraud classification. The model achieves high detection accuracy while minimizing false positives, and results are visualized through performance metrics including accuracy, precision, recall, and F1-score rendered within the web interface. The system is evaluated on publicly available payment transaction datasets. The proposed platform lowers the barrier for non-expert users to apply deep learning for fraud prevention and provides a reproducible, extensible baseline for automated fraud detection research.</span></em></p>