Using Artificial Intelligence to Detect Financial Statement Fraud in Publicly Traded Companies

Thesis Abstract

Abstract
Financial statement fraud is a serious concern that can have far-reaching implications for investors, regulators, and the overall stability of financial markets. Detecting such fraudulent activities in publicly traded companies is crucial for ensuring transparency and trust in the financial reporting process. This thesis explores the use of artificial intelligence (AI) techniques to enhance the detection of financial statement fraud in publicly traded companies. The research begins with an introduction that provides a comprehensive overview of the background of the study, highlighting the prevalence of financial statement fraud and its detrimental effects on stakeholders. The problem statement addresses the challenges associated with traditional fraud detection methods and emphasizes the need for more advanced and efficient approaches. The objectives of the study are outlined to establish a clear direction for the research, aiming to develop a robust AI-based framework for fraud detection. The limitations and scope of the study are also defined to provide a realistic set of boundaries within which the research will be conducted. Chapter two presents a thorough literature review that examines existing studies, theories, and methodologies related to financial statement fraud detection and AI applications in the field of accounting. The review encompasses ten key areas, including the types of financial statement fraud, traditional fraud detection techniques, the evolution of AI in accounting, and recent advancements in fraud detection using AI technologies. In chapter three, the research methodology is detailed, outlining the approach, design, data collection methods, and algorithms to be utilized in developing the AI-based fraud detection framework. The chapter also discusses the sample selection process, data preprocessing techniques, model training, and validation procedures to ensure the reliability and validity of the results. Additionally, ethical considerations and potential biases are addressed to maintain the integrity of the research process. Chapter four presents an in-depth discussion of the findings obtained from applying the AI-based fraud detection framework to real-world financial data from publicly traded companies. The analysis includes the performance evaluation of the AI model, detection of fraudulent patterns, identification of key risk indicators, and comparison with traditional detection methods. The chapter also examines the practical implications of the findings and provides insights into the potential benefits of implementing AI technologies in fraud detection processes. Finally, chapter five concludes the thesis by summarizing the key findings, highlighting the contributions to the field of accounting, and discussing the implications for future research and practice. The conclusion emphasizes the significance of using AI to enhance fraud detection capabilities in publicly traded companies and underscores the importance of continuous innovation and adaptation in combating financial statement fraud. In conclusion, this thesis contributes to the advancement of fraud detection practices by demonstrating the effectiveness of AI technologies in detecting financial statement fraud in publicly traded companies. The research findings have the potential to inform regulatory bodies, auditors, and financial analysts in developing more robust and efficient fraud detection mechanisms, ultimately promoting transparency and integrity in financial reporting.