Credit Risk Assessment of Small and Medium-sized Listed Companies Based on Multilayer Perceptron

DOI

10.2991/rac-18.2018.94How to use a DOI?

Keywords

multilayer perceptron; credit risk assessment; small and medium-listed companies

Abstract

According to the proportion of "non ST" and "ST" in training, this paper used the principle of multilayer perceptron (MLP) to establish some small and medium-sized enterprise credit risk assessment model based on neural network, and finally, this model was chosen to evaluate the credit risk of 114 small and medium listed companies in 2018. According to the operating conditions of listed companies, the samples are divided into two categories------"good" and "bad".For each listed company, the six first level indicators that are profitability, solvency, growth capacity, operating capacity, cash flow and capital and its sixteen two level indicators are mainly considered in this paper. The simulation results show that the correct rate of the training sample is as high as 88.5% and the correct rate of the test sample is up to 94.4%. The results are ideal.

Copyright

© 2018, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Li Dong
AU  - Zhang Mu
PY  - 2018/10
DA  - 2018/10
TI  - Credit Risk Assessment of Small and Medium-sized Listed Companies Based on Multilayer Perceptron
BT  - Proceedings of the 8th Annual Meeting of Risk Analysis Council of China Association for Disaster Prevention (RAC 2018)
PB  - Atlantis Press
SP  - 598
EP  - 603
SN  - 2352-5428
UR  - https://doi.org/10.2991/rac-18.2018.94
DO  - 10.2991/rac-18.2018.94
ID  - Dong2018/10
ER  -