Deep Learning Based Automatic Detection of Fraud Recognition Model Defects
Financial fraud is a serious problem in today's business field,in order to prevent and detect such behaviors,this study builds a financial fraud recognition model using Extreme Gradient Boosting(XGBoost)tree algorithm in deep learning.First,the study utilized the financial statement data in the Cathay Pacific database to build a comprehensive evaluation index system.Second,the financial fraud identification model was built using the XGBoost algorithm.The results of the study show that the fraud identifica-tion model constructed by XGBoost has a high accuracy of 9.11 and 9.58 respectively for the two enterprises'financial data fraud i-dentification;moreover,the XGBoost fraud model can accurately identify the financial indicators that have a greater impact on the fraud phenomenon of the enterprise,and its identification time is within 2 min.In conclusion,the fraud identification model construc-ted in this study has certain application value and is of great theoretical and practical significance for the development of financial fraud identification.
万方数据
维普
