Key points are not available for this paper at this time.
Artificial Intelligence (AI) has revolutionized financial fraud detection by providing more accurate, scalable, and adaptive systems across various sectors, including banking, insurance, and healthcare. This systematic review aims to evaluate the effectiveness of AI-based techniques in detecting financial fraud and to identify the challenges and limitations associated with their implementation. The study systematically reviewed peer-reviewed articles from major databases, employing methods like deep learning and machine learning to assess the performance of AI-driven fraud detection systems. The findings indicate that AI significantly improves real-time fraud detection and adaptability to evolving fraud patterns compared to traditional rule-based systems. However, challenges such as ethical concerns, algorithmic bias, data privacy issues, and system vulnerabilities pose barriers to widespread adoption. Additionally, scalability issues hinder smaller organizations from fully leveraging AI's potential. In conclusion, AI-based fraud detection systems offer a transformative approach to combating financial fraud. Yet, overcoming the challenges requires a focus on data quality, the development of explainable AI models, and enhancing cybersecurity measures. Policymakers and stakeholders must collaborate to create updated regulatory frameworks that support the ethical use of AI in fraud detection.
Adhikari et al. (Mon,) studied this question.