Research on the Detection of Financial Fraud Using Data Mining Techniques

Abstract

Financial information plays a crucial role for future investors to make important decisions, and how to provide true, reliable and accurate financial information becomes a top mission for enterprises. To effectively identify financial fraud information, we first select the relative indicators by reviewing the financial information of previous studies, and the indicators related to false information are prepared for data modeling using data mining tool. Furthermore, we analyze these relative indicators through the rattle package in the R and Ada Boost method. The results we obtained demonstrate that a company's solvency is the primary factor in determining whether a company has financial information fraud. Meanwhile, key factors like profitability, operating capacity, accounts receivable turnover days, business debt ratio, and financial debt ratio are useful when detecting financial information fraud.