ABSTRACT
The landscape of decision support systems is evolving rapidly, driven by technological advancements and the integration of emerging technologies like Artificial Intelligence, Machine Learning, and Big Data Analytics. This project focuses on the development of a decision support system specifically for fraud detection in organizations. Fraud is a global concern that affects organizations worldwide, causing financial losses and reputational damage. Existing fraud detection methods often struggle to keep pace with evolving fraud techniques, to address this issue, this research aims to design a decision support system that enhances the accuracy of fraud detection, reduces false positives, detects emerging fraud trends, and utilizes data from diverse sources efficiently. The research scope covers various aspects, including fraud detection methods, data integration, architecture design, model development, testing and implementation. While the significance of this study lies in its potential to enhance organizations fraud management capabilities, it is essential to recognize the system's limitations. These include the evolving nature of fraud techniques, potential false positives and negatives, challenges in detecting insider fraud, cost considerations, and the need for a holistic approach to fraud prevention. Nonetheless, a well-designed and implemented decision support system for fraud detection holds great promise in mitigating the risks associated with fraudulent activities in organizations.
