Financial fraud continues to pose a significant threat to financial institutions and individual consumers alike. Traditional rule-based systems struggle to keep pace with the evolving nature of fraudulent activities. This paper explores the potential of Artificial Neural Networks (ANNs) with a specific focus on binary classification for identifying fraudulent transactions in real-time. We propose a novel approach utilizing a powerful ANN architecture trained on historical labeled data, enabling effective and efficient detection of anomalous patterns indicative of fraud. Furthermore, the paper introduces the development of a comprehensive and user-friendly dashboard designed to seamlessly integrate with the ANN model. This interactive dashboard empowers stakeholders with real-time visualization of transaction activity, allowing for dynamic monitoring and management of flagged transactions. By combining the strengths of an advanced ANN model and a user-centric dashboard, this research proposes a comprehensive solution aimed at enhancing the accuracy and efficiency of financial fraud detection, ultimately safeguarding financial institutions and consumers from potential losses. This research signifies a valuable contribution to the field of financial fraud detection by demonstrating the effectiveness of ANNs coupled with an insightful dashboard, offering a more robust and comprehensive approach to combatting financial crime.