Bankruptcy Prediction Modeling Using Multiple Neural Network Models

November 5, 2010

Shin, K. Lee, K., Bankruptcy Prediction Modeling Using Multiple Neural Network Models, Lecture Notes in Artificial Intelligence 3214:668–674, September, 2004. – SCIE, ISSN:0302-9743

Abstract

The primary goal of this paper is to get over the limitations of single neural network models through model integration so as to increase the accuracy of bankruptcy prediction. We take the closeness of the output value to either 0 or 1 as the models confidence in its prediction as to whether or not a company is going to bankrupt. In case where multiple models yield conflicting prediction results, our integrated model takes the output value of the highest confidence as the final output. The output of the confidence-based integration approach significantly increases the prediction performance. The results of composite prediction suggest that the proposed approach will offer improved performance in business classification problems by integrating case-specific knowledge with the confidence information and general knowledge with the multi-layer perceptrons generalization capability.

Filed under Knowledge Management and Engineering, Other Publications

Neuro-genetic Approach for Bankruptcy Prediction Modeling

November 5, 2010

Shin, K. Lee, K., Neuro-genetic Approach for Bankruptcy Prediction Modeling, Lecture Notes in Artificial Intelligence 3214:646–652, September, 2004. – SCIE, ISSN:0302-9743.

Abstract  

Artificial neural network (ANN) modeling has become the dominant modeling paradigm for bankruptcy prediction. To further improve the neural networks prediction capability, the integration of the ANN models and the hybridization of ANN with relevant paradigms such as evolutionary computing has been demanded. This paper first attempted to apply neurogenetic approach to bankruptcy prediction problem for finding optimal weights and confirmed that the approach can be a good methodology though it currently could not outperform the backpropagation learning algorithm. The result of this paper shows a possibility of neurogenetic approach to bankruptcy prediction problem since the simple neurogenetic approach produced a meaningful performance.

Filed under Knowledge Management and Engineering, Other Publications

Support Vector Machines Approach to Pattern Detection in Bankruptcy Prediction and its Contingency

November 5, 2010

Shin, K., Lee, K., Kim, H., Support Vector Machines Approach to Pattern Detection in Bankruptcy Prediction and its Contingency, Lecture Notes in Computer Science 3316:1254-1259, November, 2004.  – SCIE ISSN:0302-9743. pdf

Abstract

This study investigates the effectiveness of support vector machines (SVM) approach in detecting the underlying data pattern for the corporate failure prediction tasks. Back-propagation neural network (BPN) has some limitations in that it needs a modeling art to find an appropriate structure and optimal solution and also large training set enough to search the weights of the network. SVM extracts the optimal solution with the small training set by capturing geometric characteristics of feature space without deriving weights of networks from the training data. In this study, we show the advantage of SVM approach over BPN to the problem of corporate bankruptcy prediction. SVM shows the highest level of accuracies and better generalization performance than BPN especially when the training set size is smaller.

Filed under Knowledge Management and Engineering, Other Publications

Analysis of Best Practice Policy and Benchmarking Behavior for Government Knowledge Management

November 3, 2010

Lee, K., Jeon, B., “Analysis of Best Practice Policy and Benchmarking Behavior for Government Knowledge Management,” Lecture Notes in Computer Science, pp. Vol. 3035, 70 – 79, May, 2004. – SCIE, ISSN:0302-9743. pdf

Abstract

Korean government has several best practice competition and diffusion programs for the purpose of public administration reform and the improvement of government service. From the perspective of knowledge management, this paper evaluates the best practice policy and analyzes the main factors influencing the recognition, adoption and utilization of best practices through the email-based survey and interview with local government officers. The result shows that 1) The government officers’ recognition of best practice programs and the best practices themselves is not high, 2) The adoption and utilization of a best practice is affected by its value and officer’s information needs, 3) Raising the recognition of Best practice policy affects the recognition and adoption of a best practice, and 4) The recognition and utilization of a best practice is affected by the work experience. The result gives important implications for designing and implementing government knowledge management systems and strategies.

Filed under Knowledge Management and Engineering, Other Publications

Follow

Get every new post delivered to your Inbox.