Predictive Analytics for Accounting Fraud Detection: A Study Based on Integrating Corporate Governance and Underpinning Theories
Muhammed Sameer Uddin *
School of Business and Technology, Saint Mary’s University of Minnesota, Winona, MN 55987, USA.
Omaima Eltahir Babikir Mohamed
Bank Rakyat School of Business and Entrepreneurship, Universiti Tun Abdul Razak (UNIRAZK), Kuala Lumpur, Malaysia.
John Ebert
Department of Resource Analysis, Saint Mary’s University of Minnesota, Winona, MN 55987, USA.
*Author to whom correspondence should be addressed.
Abstract
Accounting fraud is a major problem in today's dynamic financial world, particularly for stock exchange listed companies in Bangladesh. Accounting fraud undermines investor faith in the market, affects financial stability, and deteriorates market integrity, posing a major threat to the nation's economic growth. Traditional methods of detecting fraud, which depend primarily on hand audits, have proved ineffective in detecting rapid fraudulent transactions. This paper argues for the use of predictive analytics as a forward-thinking approach to detect accounting fraud before it occurs. Predictive analytics use statistical models and data mining techniques to discern patterns and anomalies in financial data, facilitating the early detection and prevention of fraudulent activity.
This study aims to create a predictive analysis model that employs essential financial indicators—namely profitability ratios, liquidity ratios, leverage ratios, and cash flow metrics—and assess their efficacy in identifying probable fraud in publicly listed companies in Bangladesh. The study also examines the mediating function of corporate governance disclosures, such as audit committee effectiveness and board independence, in improving fraud detection. This study uses a quantitative research method to turn fraud detection practices from simple compliance requirements into a strategic advantage, which improves financial transparency and strengthens investor confidence in Bangladesh's financial markets.
Keywords: Accounting fraud, predictive analytics, financial indicators, corporate governance