UCLA

Business’s accelerated globalization has weakened regulatory capacity of the law and scholars have been paid attention to fraud detection in recent years. In this study, we introduced Random Forest (RF) for financial fraud technique  detection  and  detailed  features  selection,  variables’  importance  measurement,  partial  correlation analysis and Multidimensional analysis. The results show that a combination of eight variables has the highest accuracy. The ratio of debt to equity (DEQUTY) is the most important variable in the model. Moreover, we applied  four  statistic  methodologies,  including  parametric  and  non-parametric  models  to  construct  detection models and concluded that Random Forest has the highest accuracy and the non-parametric models have higher accuracy  than  non-parametric  models.  However,  Random  Forest  can  improve  the  detection  efficiency significantly and have an important practical implication.