Applying Benford's Law to publicly traded companies in the United States from the year 2013 to 2022

Abstract

Financial fraud in financial statements is a significant concern that could have a negative impact on stakeholders such as lenders and shareholders. Benford's Law, a principle that describes the expected distribution of first digits in naturally occurring data, provides a path for detecting these fraud cases. By leveraging these anticipated patterns, analysts can uncover manipulated information, such as fabricated financial records. The study used two data sets to investigate this concept: one encompassing businesses with no allegations of financial deception and another encompassing those accused of such misconduct. The dataset included 105 records of business performance from different years obtained from an instructor and 35 cases of reported fraudulent activities within US firms. The researcher observed the financial data for adherence to Benford's Law using various statistical methods, including Mean Absolute Deviation (MAD), Kolmogorov-Smirnov (KS), and Chi square analyses. The findings show that, when compared to their legitimate counterparts, companies engaged in fraud are more likely to deviate from the expectations set by Benford's Law. This observation suggests that Benford's Law may be useful in detecting financial statement fraud. This study concludes that Benford's Law is useful for detecting financial statement fraud. However, when using Benford's Law to detect fraud, it is critical to account for additional variables. Along with applying Benford's Law, analysts should consider factors such as the company's size, volatility, and growth trajectory.