Comparison of Support Vector Machine and Back Propagation Neural Network in Evaluating the Enterprise Financial Distress - Computer Science > LearningReport as inadecuate




Comparison of Support Vector Machine and Back Propagation Neural Network in Evaluating the Enterprise Financial Distress - Computer Science > Learning - Download this document for free, or read online. Document in PDF available to download.

Abstract: Recently, applying the novel data mining techniques for evaluating enterprisefinancial distress has received much research alternation. Support VectorMachine SVM and back propagation neural BPN network has been appliedsuccessfully in many areas with excellent generalization results, such as ruleextraction, classification and evaluation. In this paper, a model based on SVMwith Gaussian RBF kernel is proposed here for enterprise financial distressevaluation. BPN network is considered one of the simplest and are most generalmethods used for supervised training of multilayered neural network. Thecomparative results show that through the difference between the performancemeasures is marginal; SVM gives higher precision and lower error rates.



Author: Ming-Chang Lee 1, Chang To 2 1 Fooyin University, Taiwan and 2 Shu-Te University, Taiwan

Source: https://arxiv.org/







Related documents