Detecting Financial Fraud using Two Types of Benford Factors: Evidence from China

Abstract

Financial fraud of listed companies can lead to anomalies in the distribution of financial data, which can be detected by Benford's Law. This study takes financial data of Chinese listed companies to construct two types of Benford factors for detecting financial fraud. The empirical results show that as the deviation of financial data distribution from Benford's law increases, the probability of financial fraud increases significantly. Furthermore, compared with rustically using traditional financial indicators, the addition of the Benford factors can effectively reduce the Type I or Type II error using the logistic regression model. Finally, we show that the identification indicators selected in this study contributes to the detection of financial fraud with the help of digital distribution laws.