A comprehensive review on insider trading detection using artificial intelligence

This paper provides a comprehensive review that delves into the domain of insider trading detection, focusing on the integration of artificial intelligence (AI) to offer insights into regulatory strategies and technological advancements aimed at safeguarding the integrity of financial markets. The systematic literature review method is employed to analyze existing research, offering a nuanced understanding of current trends and challenges in this area. The main contribution lies in offering clear perspectives on the effectiveness of machine learning (ML) and deep learning (DL) in detecting insider trading activities, providing a clear perspective on regulatory measures and technological tools. The findings highlight promising capabilities in identifying irregularities, and challenges such as data heterogeneity and regulatory variations across countries persist. The review emphasizes the need for standardized datasets, global collaboration, and enhanced regulatory frameworks to address these challenges and promote more robust insider trading detection systems. Overall, this paper contributes valuable insights into existing knowledge, providing a roadmap for future research and regulatory developments in the evolving field of financial market oversight.