Institutional Repository
Technical University of Crete
Technical University of Crete
EN
|
EL
| URI: | http://purl.tuc.gr/dl/dias/1B03D059-B99B-475B-93E1-D6386672833E | ||
| Year | 2007 | ||
| Type of Item | Peer-Reviewed Journal Publication | ||
| License |
|
||
| Bibliographic Citation | M. Marinaki, Y. Marinakis and C. Zopounidis, (2007), “Application of a Genetic Algorithm for the Credit Risk Assessment Problem”, Foundations of Computing and Decisions Sciences, Vol.32, Issue 2, pp. 139-152. URL:http://fcds.cs.put.poznan.pl/FCDS2/ArticleDetails.aspx?articleId=110 | ||
| Appears in Collections |
In this paper, a new procedure that utilizes a Genetic algorithm in order tosolve the Feature Subset Selection problem is presented. The proposed algorithm iscombined with a number of nearest neighbor based classifiers. The proposed Genetic based classification algorithm is applied for the solution of the Credit Risk AssessmentClassification problem. The performance of the algorithm is tested using data from 1411firms derived from the loan portfolio of a leading Greek Commercial Bank in order toclassify the firms in different groups representing different levels of credit risk. Acomparison of the algorithm with other classification methods, such as SVM, CART isperformed using these data. The algorithm is, also, compared with another metaheuristic algorithm. In this algorithm, the feature subset selection problem is solved using Tabu Search and in the classification phase the Nearest Neighbor Classifier is used. The results obtained using the genetic algorithm for the credit risk assessment classification problem are better than the results of all other classification methods and the metaheuristic algorithm used for the comparisons in this paper.
Copyright © DIAS 2013
