Detecting Financial Statement Fraud with Machine Learning: an Examination of Accounting Information and Corporate Governance Indicators

EasyChair Preprint 14307

Abstract

The detection of financial statement fraud remains a critical concern for regulators, investors, and organizations striving for transparency and accuracy in financial reporting. This study explores the application of machine learning techniques to enhance the identification of financial statement fraud, focusing oe integration of accounting information and corporate governance indicators. By leveraging advanced algorithms and data-driven methodologies, the research aims to uncover patterns and anomalies indicative of fraudulent activities within financial statements. The study employs a comprehensive dataset comprising historical financial records and governance metrics, applying various machine learning models such as decision trees, support vector machines, and neural networks. The performance of these models is evaluated in terms of accuracy, precision, and recall to determine their effectiveness in distinguishing between fraudulent and non-fraudulent financial statements. The findings highlight the potential of machine learning to improve fraud detection processes, offering valuable insights into the role of accounting data and governance structures in mitigating financial risks. This research contributes to the development of more robust and automated systems for fraud detection, enhancing the reliability of financial reporting and corporate governance practice

Keyphrases: Detecting Financial Statement, Machine Learning (ML), Support Vector Machines (SVM)

@booklet{EasyChair:14307,
  author    = {Abill Robert},
  title     = {Detecting Financial Statement Fraud with Machine Learning: an Examination of Accounting Information and Corporate Governance Indicators},
  howpublished = {EasyChair Preprint 14307},
  year      = {EasyChair, 2024}}