Research on the Application of Sparse Group Lasso-Support Vector Machine Method in Financial Report Fraud Identification

How to effectively identify the fraud in financial reports has been a hot issue for investors and capital market regulators. On the basis of analyzing the deficiency of the existing methods, this paper introduces the Sparse Group Lasso-Support Vector machine method into the field of financial report fraud Identification. According to the characteristics of this method, taking the data of listed companies in China from 2008 to 2018 as a sample, and according to the main factors affecting the fraud risk of financial reports, this paper puts forward 15 financial indicators and non-financial indicators to construct an explanatory variable set, then, this paper makes an empirical analysis by using this method. The results show that the method has higher recognition rate and interpretability than other methods, such as Logistic regression, lasso-Support vector machine and Group lasso-Support vector machine, when the explanatory variables have natural grouping structure and higher group correlation level, it has strong theoretical and practical value.