Comparison of Support Vector Machine and Back Propagation Neural Network in Evaluating the Enterprise Financial Distress

TL;DR

This paper compares Support Vector Machine and Back Propagation Neural Network models for evaluating enterprise financial distress, finding SVM slightly outperforms BPN in precision and error rates.

Contribution

It introduces a model based on SVM with Gaussian RBF kernel for financial distress evaluation and compares its performance with BPN.

Findings

SVM achieves higher precision than BPN.

SVM has lower error rates.

Performance differences are marginal.

Abstract

Recently, applying the novel data mining techniques for evaluating enterprise financial distress has received much research alternation. Support Vector Machine (SVM) and back propagation neural (BPN) network has been applied successfully in many areas with excellent generalization results, such as rule extraction, classification and evaluation. In this paper, a model based on SVM with Gaussian RBF kernel is proposed here for enterprise financial distress evaluation. BPN network is considered one of the simplest and are most general methods used for supervised training of multilayered neural network. The comparative results show that through the difference between the performance measures is marginal; SVM gives higher precision and lower error rates.