Hybrid AI Model for Online Payment Fraud Detection Using Machine Learning

The rapid growth of digital payment systems has significantly increased the convenience of financial transactions while simultaneously exposing users and institutions to rising risks of fraudulent activities. Traditional rule-based fraud detection systems are inadequate in identifying complex and evolving fraud patterns due to their static nature and high false-positive rates. This paper proposes a Hybrid Artificial Intelligence (AI) Model for online payment fraud detection that integrates rule-based systems, supervised machine learning classification, and unsupervised anomaly detection techniques into a unified framework. The model leverages historical transaction data and behavioral patterns to accurately detect fraudulent activities in real time. Experimental analysis demonstrates improved accuracy, reduced false positives, and enhanced adaptability compared to conventional methods. The proposed system offers a scalable and efficient solution suitable for modern financial ecosystems.