Abstract: With the rapid growth of e-commerce and online financial services, digital payments have become an integral part of daily transactions. However, this convenience also increases the risk of fraudulent activities such as identity theft, phishing, fake transactions, and unauthorized access. Fraud detection in digital payments is therefore a critical challenge to ensure secure and trustworthy financial systems. This research/project focuses on developing intelligent fraud detection mechanisms using advanced techniques like machine learning, deep learning, and data mining.

By analyzing transaction patterns, user behavior, and anomaly detection, the proposed system can identify suspicious activities in real-time. Various supervised and unsupervised learning algorithms are applied to classify transactions as genuine or fraudulent. Additionally, feature engineering and model optimization techniques are employed to improve accuracy and reduce false positives. The outcome of this study aims to provide a reliable fraud detection framework that enhances the security of digital payments, reduces financial losses, and builds customer trust in online transactions. The system can be integrated into banking applications, e-wallets, and other financial platforms for real-world implementation.

Downloads: | DOI: 10.17148/IARJSET.2025.12938