A tuning method for the architecture of neural network models incorporating GAM and GA as applied to bankruptcy prediction

Authors:
Chulwoo Jeong;Jae H. Min;Myung Suk Kim
Affiliations:
Graduate School of Management of Technology, Sogang University, Seoul, Republic of Korea;Sogang Business School, Sogang University, Seoul, Republic of Korea;Service Systems Management & Engineering Dept., Sogang Business School, Sogang University, Seoul, Republic of Korea
Venue:
Expert Systems with Applications: An International Journal
Year:
2012

Citing 17
Cited 4

Learning translation invariant recognition in massively parallel networks

Volume I: Parallel architectures on PARLE: Parallel Architectures and Languages Europe
Multilayer feedforward networks are universal approximators

Neural Networks
Neural networks and the bias/variance dilemma

Neural Computation
Practical neural network recipes in C++

Practical neural network recipes in C++
An experimental evaluation of neural networks for classification

Computers and Operations Research
Managerial applications of neural networks: the case of bank failure predictions

Management Science
Feedforward artificial neural networks for solving discrete multiple criteria decision making problems

Management Science
Hybrid neural network models for bankruptcy predictions

Decision Support Systems
Determining the saliency of input variables in neural network classifiers

Computers and Operations Research
Using Feature Construction to Improve the Performance of Neural Networks

Management Science
Prediction intervals for neural networks via nonlinear regression

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

Computers and Operations Research
Bankruptcy prediction by generalized additive models: Research Articles

Applied Stochastic Models in Business and Industry
Effects of feature construction on classification performance: An empirical study in bank failure prediction

Expert Systems with Applications: An International Journal
Bankruptcy prediction using support vector machine with optimal choice of kernel function parameters

Expert Systems with Applications: An International Journal
Bankruptcy prediction for credit risk using neural networks: A survey and new results

IEEE Transactions on Neural Networks
Backpropagation neural nets with one and two hidden layers

IEEE Transactions on Neural Networks

Bayesian dynamic linear modeling for exploring the impact of recent financial crisis on Japan Credit Default Swap market

Expert Systems with Applications: An International Journal
A statistical modeling methodology for the analysis of term structure of credit risk and its dependency

Expert Systems with Applications: An International Journal
Novel feature selection methods to financial distress prediction

Expert Systems with Applications: An International Journal
Hybrid classification and regression models via particle swarm optimization auto associative neural network based nonlinear PCA

International Journal of Hybrid Intelligent Systems

Quantified Score

Hi-index	12.06

Visualization

Abstract

The performance of a neural network model is affected by important constituent elements such as input variables, the number of hidden nodes, and the value of the decay constant. This paper suggests a new approach to fine-tune these factors to improve their accuracy. For the input variable selection, the generalized additive model (GAM) is applied. The grid search method and the genetic algorithm are sequentially implemented to fine-tune the number of hidden nodes and the value of the weight decay parameters. This suggested method to improve the neural network model is used to predict the probability that a firm may apply for bankruptcy, and its performance is compared with the results of existing bankruptcy forecasting models such as case-based reasoning, the decision tree, the GAM, the generalized linear model, the multi-variate discriminant analysis, and the support vector machine. Our empirical results indicate that the newly tuned neural network model significantly outperforms the other models.