Application of Benford's Law to Detect Fraud in Customers’ Ending Balances Using First Digit Test, Second Digit Test, and First Two Digits Test

Source abstract

Bank fraud involves several actions such as manipulating duplication, forgery, changing accounting records and so on. This study aims to detect the potential for fraud in banking reports on customer final balances. The types of tests used to detect potential fraud in this study are the First Digit Test, Second Digit Test and First Two Digit Test Benford's Law. Benford's law states that the proportion of occurrences of numbers in certain numbers is not the same. In addition to the three Benford's Law tests, further statistical tests were carried out to determine the magnitude of the deviation between the actual proportion of occurrences and the expected proportion of Benford's Law using the Mean Absolute Deviation (MAD), Chi-square test, and Z test. This study uses secondary data on the final balance of customer deposits as of July 2023 as much as 20,105 data. The results showed that there were indications of fraud in the form of rounding and duplication of data on the customer's final balance. MAD results show that the proportion of occurrence of actual numbers is quite consistent with the proportion of occurrence of Benford's Law expectations. Based on the Z test, the balance that has the potential for fraud is the value with the first digit '5', the second digit '3' and the first two digits '23'. These numbers can be found in balances with a nominal value of Rp5000 and Rp5636 in the first digit '5', and Rp23038 in the second digit '3' and the first two digits '23'.