Research Information System
Engineering, Technology and Applied Science Research, vol.16, no.1, pp.31585-31590, 2026 (Scopus)
Financial fraud is one of the most crucial challenges in the digital economy, with growing cutting-edge attacks threatening the security of online transactions. Since conventional fraud detection models are often inadequate in identifying advanced fraud schemes, Advanced fraud detection approaches are required to prevent and recognize fraud in real time. In recent years, the progression of AI methods has received considerable attention in the financial sector, specifically in Financial Fraud Detection (FFD). Furthermore, Explainable AI (XAI) has become a prerequisite for building trust and driving acceptance of AI methods in high-stakes domains, namely credit risks, financial crime, and healthcare, which require reliability, fairness, and safety. This study presents an Optimization-Based Deep Belief Network for Fraud Detection in Financial Transaction Systems (ODBN-FDFTS) approach, aiming to develop a reliable system for detecting financial transaction fraud. The ODBN-FDFTS approach begins with data preprocessing using a standard scaler to normalize financial transaction records and enhance data quality. The Artificial Rabbit Optimization (ARO) technique is employed for Feature Selection (FS), and a Deep Belief Network (DBN) is used for the financial fraud classification process, tuning its hyperparameters using the Butterfly Optimization Algorithm (BOA). LIME is integrated to provide transparency and interpretability in the fraud detection process. The comparison study of the ODBN-FDFTS model showed a superior accuracy of 97.95% over other methods on the FFD dataset.