Authors:
Paulius Danenas
and
Gintautas Garsva
Affiliation:
Vilnius University, Lithuania
Keyword(s):
Support Vector Machines, Linear SVM, Particle Swarm Optimization, Credit Risk, Evaluation, Bankruptcy, Machine Learning.
Related
Ontology
Subjects/Areas/Topics:
Artificial Intelligence
;
Artificial Intelligence and Decision Support Systems
;
Biomedical Engineering
;
Biomedical Signal Processing
;
Computational Intelligence
;
Enterprise Information Systems
;
Health Engineering and Technology Applications
;
Human-Computer Interaction
;
Industrial Applications of Artificial Intelligence
;
Methodologies and Methods
;
Neural Network Software and Applications
;
Neural Networks
;
Neurocomputing
;
Neurotechnology, Electronics and Informatics
;
Pattern Recognition
;
Physiological Computing Systems
;
Sensor Networks
;
Signal Processing
;
Soft Computing
;
Theory and Methods
Abstract:
A research on credit risk evaluation modelling using linear Support Vector Machines (SVM) classifiers is proposed in this paper. The classifier selection is automated using Particle Swarm Optimization technique. Sliding window approach is applied for testing classifier performance, together with other techniques such as discriminant analysis based scoring for evaluation of financial instances and correlation-based feature selection. The developed classifier is applied and tested on real bankruptcy data showing promising results.