Artificial neural network vs linear discriminant analysis in credit ratings forecast: A comparative study of prediction performances

Kuldeep Kumar, Sukanto Bhattacharya

Research output: Contribution to journalArticleResearchpeer-review

62 Citations (Scopus)

Abstract

Purpose The purpose of this paper is to perform a comparative study of prediction performances of an artificial neutral network (ANN) model against a linear prediction model like a linear discriminant analysis (LDA) with regards to forecasting corporate credit ratings from financial statement data. Design/methodology/approach The ANN model used in the study is a fully connected back-propagation model with three layers of neurons. The paper uses a comparative approach whereby two prediction models – one based on ANN and the other based on LDA are developed using identically partitioned data set. Findings The study found that the ANN model comprehensively outperformed the LDA model in both training and test partitions of the data set. While the LDA model may have been hindered by omitted variables; this actually lends further credence to the ANN model showing that the latter is more robust in dealing with missing data. Research limitations/implications A possible drawback in the model implementation probably lies in the selection of the various accounting ratios. Perhaps future replications of this study should look more carefully at choosing the ratios after duly addressing the problems of collinearity and duplications more rigorously. Practical implications The findings of this study imply that since ANN models can better deal with complex data sets and do not require restraining assumptions like linearity and normality, it may be overall a better approach in corporate credit rating forecasts that uses large financial data sets. Originality/value This study brings out the effectiveness of non-linear pattern learning models as compared to linear ones in forecasts of financial solvency. This goes on to further highlight the practical importance of the new breed of computational tools available to techno-savvy financial analysts and also to the providers of corporate credit.

Original languageEnglish
Pages (from-to)216-227
Number of pages12
JournalReview of Accounting and Finance
Volume5
Issue number3
DOIs
Publication statusPublished - 1 Jul 2006

Fingerprint

Artificial neural network
Comparative study
Prediction
Discriminant analysis
Credit rating
Network model
Prediction model
Solvency
Learning model
Back propagation
Neuron
Missing data
Replication
Collinearity
Financial analysts
Normality
Design methodology
Financial statements
Credit
Linearity

Cite this

@article{1d9175ef4d96465293a9297cfc3ef40d,
title = "Artificial neural network vs linear discriminant analysis in credit ratings forecast: A comparative study of prediction performances",
abstract = "Purpose The purpose of this paper is to perform a comparative study of prediction performances of an artificial neutral network (ANN) model against a linear prediction model like a linear discriminant analysis (LDA) with regards to forecasting corporate credit ratings from financial statement data. Design/methodology/approach The ANN model used in the study is a fully connected back-propagation model with three layers of neurons. The paper uses a comparative approach whereby two prediction models – one based on ANN and the other based on LDA are developed using identically partitioned data set. Findings The study found that the ANN model comprehensively outperformed the LDA model in both training and test partitions of the data set. While the LDA model may have been hindered by omitted variables; this actually lends further credence to the ANN model showing that the latter is more robust in dealing with missing data. Research limitations/implications A possible drawback in the model implementation probably lies in the selection of the various accounting ratios. Perhaps future replications of this study should look more carefully at choosing the ratios after duly addressing the problems of collinearity and duplications more rigorously. Practical implications The findings of this study imply that since ANN models can better deal with complex data sets and do not require restraining assumptions like linearity and normality, it may be overall a better approach in corporate credit rating forecasts that uses large financial data sets. Originality/value This study brings out the effectiveness of non-linear pattern learning models as compared to linear ones in forecasts of financial solvency. This goes on to further highlight the practical importance of the new breed of computational tools available to techno-savvy financial analysts and also to the providers of corporate credit.",
author = "Kuldeep Kumar and Sukanto Bhattacharya",
year = "2006",
month = "7",
day = "1",
doi = "10.1108/14757700610686426",
language = "English",
volume = "5",
pages = "216--227",
journal = "Review of Accounting and Finance",
issn = "1475-7702",
publisher = "Emerald Group Publishing Ltd.",
number = "3",

}

Artificial neural network vs linear discriminant analysis in credit ratings forecast : A comparative study of prediction performances. / Kumar, Kuldeep; Bhattacharya, Sukanto.

In: Review of Accounting and Finance, Vol. 5, No. 3, 01.07.2006, p. 216-227.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - Artificial neural network vs linear discriminant analysis in credit ratings forecast

T2 - A comparative study of prediction performances

AU - Kumar, Kuldeep

AU - Bhattacharya, Sukanto

PY - 2006/7/1

Y1 - 2006/7/1

N2 - Purpose The purpose of this paper is to perform a comparative study of prediction performances of an artificial neutral network (ANN) model against a linear prediction model like a linear discriminant analysis (LDA) with regards to forecasting corporate credit ratings from financial statement data. Design/methodology/approach The ANN model used in the study is a fully connected back-propagation model with three layers of neurons. The paper uses a comparative approach whereby two prediction models – one based on ANN and the other based on LDA are developed using identically partitioned data set. Findings The study found that the ANN model comprehensively outperformed the LDA model in both training and test partitions of the data set. While the LDA model may have been hindered by omitted variables; this actually lends further credence to the ANN model showing that the latter is more robust in dealing with missing data. Research limitations/implications A possible drawback in the model implementation probably lies in the selection of the various accounting ratios. Perhaps future replications of this study should look more carefully at choosing the ratios after duly addressing the problems of collinearity and duplications more rigorously. Practical implications The findings of this study imply that since ANN models can better deal with complex data sets and do not require restraining assumptions like linearity and normality, it may be overall a better approach in corporate credit rating forecasts that uses large financial data sets. Originality/value This study brings out the effectiveness of non-linear pattern learning models as compared to linear ones in forecasts of financial solvency. This goes on to further highlight the practical importance of the new breed of computational tools available to techno-savvy financial analysts and also to the providers of corporate credit.

AB - Purpose The purpose of this paper is to perform a comparative study of prediction performances of an artificial neutral network (ANN) model against a linear prediction model like a linear discriminant analysis (LDA) with regards to forecasting corporate credit ratings from financial statement data. Design/methodology/approach The ANN model used in the study is a fully connected back-propagation model with three layers of neurons. The paper uses a comparative approach whereby two prediction models – one based on ANN and the other based on LDA are developed using identically partitioned data set. Findings The study found that the ANN model comprehensively outperformed the LDA model in both training and test partitions of the data set. While the LDA model may have been hindered by omitted variables; this actually lends further credence to the ANN model showing that the latter is more robust in dealing with missing data. Research limitations/implications A possible drawback in the model implementation probably lies in the selection of the various accounting ratios. Perhaps future replications of this study should look more carefully at choosing the ratios after duly addressing the problems of collinearity and duplications more rigorously. Practical implications The findings of this study imply that since ANN models can better deal with complex data sets and do not require restraining assumptions like linearity and normality, it may be overall a better approach in corporate credit rating forecasts that uses large financial data sets. Originality/value This study brings out the effectiveness of non-linear pattern learning models as compared to linear ones in forecasts of financial solvency. This goes on to further highlight the practical importance of the new breed of computational tools available to techno-savvy financial analysts and also to the providers of corporate credit.

UR - http://www.scopus.com/inward/record.url?scp=84992933570&partnerID=8YFLogxK

U2 - 10.1108/14757700610686426

DO - 10.1108/14757700610686426

M3 - Article

VL - 5

SP - 216

EP - 227

JO - Review of Accounting and Finance

JF - Review of Accounting and Finance

SN - 1475-7702

IS - 3

ER -