Estimation of the Efficiency of Knowledge Acquisition Techniques Using Clustering

Proceedings of the Ninth International Scientific School MA SR - 2011 2011
Peteris Grabusts, Inese Poļaka

Prediction of corporate bankruptcy is a study topic of great interest. There is no general method which would allow one to forecast unfavourable consequence with a high confidence degree. This paper focuses on the analysis of the approaches that can be used to perform an early bankruptcy risk prediction - in previous research multivariate discriminant analysis (MDA), neural network based approach, early potential function method have been used. Lately, time series clustering approach has become popular and its feasibility for bankruptcy data analysis is being investigated. Experiments are performed that validate the use of such methods in the given class of tasks.

Atslēgas vārdi
bankruptcy, financial ratio, MDA, neural networks, time series, clustering

Grabusts, P., Poļaka, I. Estimation of the Efficiency of Knowledge Acquisition Techniques Using Clustering. No: Proceedings of the Ninth International Scientific School MA SR - 2011, Krievija, Saint Petersburg, 28. Jūn-2. Jūl., 2011. Saint Petersburg: IPME RAS, 2011, 131.-137.lpp. ISBN 9785808806276.

Publikācijas valoda
English (en)