Credit scoring model based on multilayer perceptron

Author

Pang, Sulin ; Wang, Yanming ; Bai, Yuanhuai

Author_Institution

Dept. of Math., Jinan Univ., Guangzhou, China

fYear

2003

fDate

8-8 Oct. 2003

Firstpage

501

Lastpage

505

Abstract

The research establishes a neural network credit scoring model based on the principle of multilayer perceptron (MLP). It is used to evaluate the credit of 96 listed companies. The listed companies are divided into three groups: a "good" group, a "middle" group and a "bad" group according to their management situations. To each listed company, we consider four primary financial indexes: income per share, net asset per share, return rate of net asset, and cash flow per share. All data come from the annals of listed company in 2000. The simulation results show that the classification correction rate of the neural network credit scoring model is 79.17%. In addition, we give the learning algorithm and step of the model in detail and analyse the experimental results.

Keywords

financial management; learning (artificial intelligence); multilayer perceptrons; neural nets; statistical distributions; cash flow per share; financial indexes; financial management; income per share; learning algorithm; multilayer perceptron; net asset per share; net asset return rate; neural network credit scoring model; statistical distributions;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Control. 2003 IEEE International Symposium on

Conference_Location

Houston, TX, USA

ISSN

2158-9860

Print_ISBN

0-7803-7891-1

Type

conf

DOI

10.1109/ISIC.2003.1254686

Filename

1254686