A threshold-varying artificial neural network approach for classification and its application to bankruptcy prediction problem

Research output: Contribution to journalArticle

92 Citations (Scopus)

Abstract

We propose a threshold-varying artificial neural network (TV-ANN) approach for solving the binary classification problem. Using a set of simulated and real-world data set for bankruptcy prediction, we illustrate that the proposed TV-ANN fares well, both for training and holdout samples, when compared to the traditional backpropagation artificial neural network (ANN) and the statistical linear discriminant analysis. The performance comparisons of TV-ANN with a genetic algorithm-based ANN and a classification tree approach C4.5 resulted in mixed results.

Original languageEnglish (US)
Pages (from-to)2561-2582
Number of pages22
JournalComputers and Operations Research
Volume32
Issue number10
DOIs
StatePublished - Oct 1 2005

Fingerprint

Bankruptcy
Artificial Neural Network
Neural networks
Prediction
Classification Tree
Binary Classification
Back-propagation Neural Network
Performance Comparison
Discriminant analysis
Discriminant Analysis
Backpropagation
Classification Problems
Genetic algorithms
Bankruptcy prediction
Artificial neural network
Genetic Algorithm

All Science Journal Classification (ASJC) codes

  • Computer Science(all)
  • Modeling and Simulation
  • Management Science and Operations Research

Cite this

@article{e577b865c5734991a5e17583099d3ee5,
title = "A threshold-varying artificial neural network approach for classification and its application to bankruptcy prediction problem",
abstract = "We propose a threshold-varying artificial neural network (TV-ANN) approach for solving the binary classification problem. Using a set of simulated and real-world data set for bankruptcy prediction, we illustrate that the proposed TV-ANN fares well, both for training and holdout samples, when compared to the traditional backpropagation artificial neural network (ANN) and the statistical linear discriminant analysis. The performance comparisons of TV-ANN with a genetic algorithm-based ANN and a classification tree approach C4.5 resulted in mixed results.",
author = "Pendharkar, {Parag C.}",
year = "2005",
month = "10",
day = "1",
doi = "10.1016/j.cor.2004.06.023",
language = "English (US)",
volume = "32",
pages = "2561--2582",
journal = "Computers and Operations Research",
issn = "0305-0548",
number = "10",

}

TY - JOUR

T1 - A threshold-varying artificial neural network approach for classification and its application to bankruptcy prediction problem

AU - Pendharkar, Parag C.

PY - 2005/10/1

Y1 - 2005/10/1

N2 - We propose a threshold-varying artificial neural network (TV-ANN) approach for solving the binary classification problem. Using a set of simulated and real-world data set for bankruptcy prediction, we illustrate that the proposed TV-ANN fares well, both for training and holdout samples, when compared to the traditional backpropagation artificial neural network (ANN) and the statistical linear discriminant analysis. The performance comparisons of TV-ANN with a genetic algorithm-based ANN and a classification tree approach C4.5 resulted in mixed results.

AB - We propose a threshold-varying artificial neural network (TV-ANN) approach for solving the binary classification problem. Using a set of simulated and real-world data set for bankruptcy prediction, we illustrate that the proposed TV-ANN fares well, both for training and holdout samples, when compared to the traditional backpropagation artificial neural network (ANN) and the statistical linear discriminant analysis. The performance comparisons of TV-ANN with a genetic algorithm-based ANN and a classification tree approach C4.5 resulted in mixed results.

UR - http://www.scopus.com/inward/record.url?scp=13544265385&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=13544265385&partnerID=8YFLogxK

U2 - 10.1016/j.cor.2004.06.023

DO - 10.1016/j.cor.2004.06.023

M3 - Article

AN - SCOPUS:13544265385

VL - 32

SP - 2561

EP - 2582

JO - Computers and Operations Research

JF - Computers and Operations Research

SN - 0305-0548

IS - 10

ER -