基于分类回归树的企业会计信息失真识别方法

A Method for Identifying Accounting Information Distortion in Enterprises Based on Classification Regression Tree

常规的企业会计信息失真识别方法主要使用svmtrain惩罚参数进行识别交叉验证,易受核函数参数影响,导致平均识别错误率较高,因此急需基于分类回归树设计一种全新的企业会计信息失真识别方法。文章通过定量分析法选取了会计信息失真识别变量,利用分类回归树构建企业会计信息失真识别模型,设计企业会计信息失真识别算法,从而实现了企业会计信息失真识别。实验结果表明,设计的基于分类回归树的企业会计信息失真识别方法在不同会计失真识别变量下的平均识别错误率均较低,证明设计的企业会计信息失真分类回归树识别方法的识别效果较好,具有较高的准确性,有一定的应用价值。

Conventional methods for identifying accounting information distortion in enterprises mainly use the svmtrain penalty parameter for cross validation,which is susceptible to the influence of kernel function parameters and leads to a high average recognition error rate.Therefore,it is necessary to design a new method for identifying accounting information distortion in enterprises based on classification regression trees.The quantitative analysis method was used to select variables for identifying accounting information distortion,and a classification regression tree was used to construct a model for identifying accounting information distortion in enterprises.An algorithm for identifying accounting information distortion in enterprises was designed,thus achieving the recognition of accounting information distortion in enterprises.The experimental results show that the average recognition error rate of the enterprise accounting information distortion recognition method based on classification regression tree designed in this article is low under different accounting distortion recognition variables.This proves that the recognition effect of the designed enterprise accounting information distortion classification regression tree recognition method is good,has accuracy,and has certain application value.