Performance Evaluation of Neural Network Decision Models

Jain, Bharat A.; Nag, Barin N.

doi:10.1080/07421222.1997.11518171

“…Compare to the result of (Jain and Nag, 1997) where BPNN has 10% accuracy rate higher than both MDA and dynamic logistic model, the result of our model is not consistence. One of the reasons could be the selection of transfer function in the two hidden layers.…”

Section: Results Of Pbnn Modelmentioning

confidence: 93%

Bankruptcy Prediction of Industrial Industry in the UK

Nok¹

2017

Sriwijaya Int. J. of Dynamic Eco. And Buss.

0

View full text Add to dashboard Cite

We make comparison between 6 models including (1) Altman's (1968) z-score; (2) Model 1: z-score model with adjusted coefficients; (3) Model 2: z-score model with modified variables; (4) Model 3: dynamic logic model; (5) Merton distance to default (DD) model (Bharath & Shumway, 2008) and (6) backpropagation network model (Lippman, 1987). We assess the relative information content of these models regarding their bankruptcy prediction capability. Our tests show that dynamic logic model and DD model both provide significantly more information than the others while DD model has the highest prediction accuracy in the out of sample test. It is also worth noticing that altering coefficients and adjusting variables of the original z-score model could not significantly improve the predictive power of z-score model regarding companies in the industrial industry in the UK.

show abstract

“…In finance neural networks have been applied to the area of firm failure or bankruptcy prediction, where the emphasis is essentially on feature extraction. In solving classification problems for prediction of bankruptcy there have been results to suggest that though neural networks perform better than statistical models, their dependence on the nature of training data makes for an argument for their application in conjunction with statistical models (Jain & Nag 1997). This has already been tested in applications of non-linear partial least square regression using a neural network structure for other areas.…”

Section: Neural Network An Overviewmentioning

confidence: 99%

Product Cost Management Structures: a review and neural network modelling

Jha

¹

,

Montague²,

Glassey³

et al. 2003

AJIS

0

View full text Add to dashboard Cite

This paper reviews the growth of approaches in product costing and draws synergies with information management and resource planning systems, to investigate potential application of state of the art modelling techniques of neural networks. Increasing demands on costing systems to serve multiple decision-making objectives, have made it essential to use better techniques for analysis of available data. This need is highlighted in the paper. The approach of neural networks, which have several analogous facets to complement and aid the information demands of modern product costing, Enterprise Resource Planning (ERP) structures and the dominant-computing environment (for information management in the object oriented paradigm) form the domain for investigation. Simulated data is used in neural network applications across activities that consume resources and deliver products, to generate information for monitoring and control decisions. The results in application for feature extraction and variation detection and their implications are presented in the paper.

show abstract

“…A number of recent research claimed neutral network analysis to have a higher predictive capability (Jain and Barin, 1997). This model is therefore expected to be outperforming the entire previously mentioned model in classification test.…”

Section: Hypothesis Of Bpnn Modelmentioning

confidence: 99%

Bankruptcy Prediction of Industrial Industry in the UK

Nok¹

2017

Sriwijaya Int. J. of Dynamic Eco. And Buss.

View full text Add to dashboard Cite

We make comparison between 6 models including (1) Altman's (1968) z-score; (2) Model 1: z-score model with adjusted coefficients; (3) Model 2: z-score model with modified variables; (4) Model 3: dynamic logic model; (5) Merton distance to default (DD) model (Bharath & Shumway, 2008) and (6) backpropagation network model (Lippman, 1987). We assess the relative information content of these models regarding their bankruptcy prediction capability. Our tests show that dynamic logic model and DD model both provide significantly more information than the others while DD model has the highest prediction accuracy in the out of sample test. It is also worth noticing that altering coefficients and adjusting variables of the original z-score model could not significantly improve the predictive power of z-score model regarding companies in the industrial industry in the UK.

show abstract

Performance Evaluation of Neural Network Decision Models

Cited by 69 publications

References 22 publications

Bankruptcy Prediction of Industrial Industry in the UK

Bankruptcy Prediction of Industrial Industry in the UK

Product Cost Management Structures: a review and neural network modelling

Bankruptcy Prediction of Industrial Industry in the UK

Contact Info

Product

Resources

About