Credit Prediction Using Transfer of Learning via Self-Organizing Maps to Neural Networks
For financial institutions, the ability to predict or forecast business failures is crucial, as incorrect decisions can have direct financial consequences. Credit prediction and credit scoring are the two major research problems in the accounting and finance domain. A variety of pattern recognition techniques including neural networks, decision trees and support vector machines have been applied to predict whether borrowers are in danger of bankruptcy and whether they should be considered a good or bad credit risk.
In this paper a clustering and unsupervised method named Self Organizing Map (SOM) is used. We propose to label each cluster with voted method and improve labeling process by training a feedforward Neural Network (NN). The approach uses transfer of learning via SOM to the NN, is tested on the Australian Credit Approval financial data set. We compare both approaches and we will discuss which one is the best prediction model for financial data.
KeywordsCredit scoring Self-organizing map Neural networks Financial risk analysis Transfer learning
Unable to display preview. Download preview PDF.
- 2.Greene, W.H.: A statistical model for credit scoring. NYU Working Paper No. EC-92-29 (1992)Google Scholar
- 3.Davidian, D.: Feed forward neural network. Google Patents, US Patent 5, 438, 646 (1995)Google Scholar
- 4.Dietterich, T.G., Bakiri, G.: Solving multiclass learning problems via error-correcting output codes. Journal of Artificial Intelligence Research, 263–286 (1995)Google Scholar
- 5.Vapnik, V.N.: Statistical Learning Theory. John Wiley & Sons, Inc. (1998)Google Scholar
- 7.Japkowicz, N.: Supervised learning with unsupervised output separation. In: International Conference on Artificial Intelligence and Soft Computing, vol. 3, pp. 321–325 (2002)Google Scholar
- 8.Merkevičius, E., Garšva, G., Simutis, R.: Forecasting of credit classes with the self-organizing maps. Informaciens Technologijos 4(33), Valdymas (2004)Google Scholar
- 15.Merkevičius, E., Garšva, G., Simutis, R.: Forecasting of credit classes with the Self-Organizing Maps. Information Technology and Control 33(4) (2015)Google Scholar
- 17.UCI Machine Learning Repository. archive.ics.uci.edu/ml/datasets/Statlog+%28Australian+Credit+Approval%29