Empirical Study on Financial Risk Identification of Chinese Listed Companies Based on ART-2 and SOFM Neural Network Model

Abstract

This paper aims at comparing Adaptive Resonance Theory ("ART" for short) and Self-organizing Feature Map ("SOFM" for short) of neural network on the study of Chinese listed company's financial risk identification. The empirical results show that the ART-2 neural network model has better recognition effect than Logistic statistical model, BP and PNN network algorithm, while the SOFM network algorithm is better than ART-2.