Title: Effective Sorting of Business Transactions Using AI for Fraud Detection and Threat Assessment
Authors: Nesreen S. Aljerjawi and Samy S. Abu-Naser
Volume: 9
Issue: 8
Pages: 139-146
Publication Date: 2025/08/28
Abstract:
This research paper explores the application of Artificial Intelligence (AI) for the efficient classification and processing of financial transactions to enhance fraud detection and risk assessment. Traditional rule-based systems often fall short in identifying sophisticated fraudulent activities due to their static nature and inability to adapt to evolving fraud patterns. This paper investigates how advanced AI and machine learning (ML) algorithms, such as Random Forest, Decision Trees, XGBoost, and deep learning, can analyze vast datasets of financial transactions in real-time to identify anomalies and suspicious patterns. We delve into the methodologies employed by these AI models, focusing on their ability to classify transactions as legitimate or fraudulent with high accuracy, thereby minimizing financial losses and reducing false positives. Furthermore, the paper examines real-world case studies where financial institutions have successfully leveraged AI to revolutionize their fraud detection processes. It also addresses critical considerations such as data imbalance and the growing importance of Explainable AI (XAI) in ensuring transparency and trust in automated fraud detection systems. The ultimate goal is to demonstrate the transformative potential of AI in creating robust, adaptive, and efficient frameworks for financial fraud detection and risk mitigation.