Municipal credit rating modelling by neural networks

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216275%3A25410%2F11%3A39892236" target="_blank" >RIV/00216275:25410/11:39892236 - isvavai.cz</a>

Result on the web

<a href="http://dx.doi.org/10.1016/j.dss.2010.11.033" target="_blank" >http://dx.doi.org/10.1016/j.dss.2010.11.033</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1016/j.dss.2010.11.033" target="_blank" >10.1016/j.dss.2010.11.033</a>

Result language

angličtina

Original language name

Municipal credit rating modelling by neural networks

Original language description

The paper presents the modelling possibilities of neural networks on a complex real-world problem, i.e. municipal credit rating modelling. First, current approaches in credit rating modelling are introduced. Second, previous studies on municipal credit rating modelling are analyzed. Based on this analysis, the model is designed to classify US municipalities (located in the State of Connecticut) into rating classes. The model includes data pre-processing, the selection process of input variables, and thedesign of various neural networks' structures for classification. The selection of input variables is realized using genetic algorithms. The input variables are extracted from financial statements and statistical reports in line with previous studies. These variables represent the inputs of neural networks, while the rating classes from Moody's rating agency stand for the outputs. In addition to exact rating classes, data are also labelled by four basic rating classes. As a result, the

Czech name

—

Czech description

—

Type

J_x - Unclassified - Peer-reviewed scientific article (Jimp, Jsc and Jost)

CEP classification

IN - Informatics

OECD FORD branch

—

Project

<a href="/en/project/GP402%2F09%2FP090" target="_blank" >GP402/09/P090: Modelling of Municipal Finance by Computational Intelligence Methods</a><br>

Continuities

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Publication year

2011

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Name of the periodical

Decision Support Systems

ISSN

0167-9236

e-ISSN

—

Volume of the periodical

51

Issue of the periodical within the volume

1

Country of publishing house

NL - THE KINGDOM OF THE NETHERLANDS

Number of pages

11

Pages from-to

108-118

UT code for WoS article

—

EID of the result in the Scopus database

—