Genetic algorithms for credit scoring: Alternative fitness function performance comparison

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F60460709%3A41340%2F15%3A65184" target="_blank" >RIV/60460709:41340/15:65184 - isvavai.cz</a>
Result on the web
<a href="http://dx.doi.org/10.1016/j.eswa.2014.11.028" target="_blank" >http://dx.doi.org/10.1016/j.eswa.2014.11.028</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1016/j.eswa.2014.11.028" target="_blank" >10.1016/j.eswa.2014.11.028</a>

Result language
angličtina
Original language name
Genetic algorithms for credit scoring: Alternative fitness function performance comparison
Original language description
Credit scoring methods have been widely investigated by researchers; recently, genetic algorithms have 23 attracted particular attention. Many research papers comparing the performance of genetic algorithms 24 and traditional scoring techniques have beenpublished, but most do not provide enough detail about 25 the fitness function used by the genetic algorithm?despite the fact that fitness function has a key influ- 26 ence on the model?s overall performance. The aim of this paper is to evaluate the predictive performance 27 of different fitness functions used by genetic algorithms in credit scoring. An alternative fitness function 28 based on a variable bitmask is proposed, and its performance then compared with fitness functions based 29 on a polynomial equation as well as an estimation of parameter range. The results suggest that the bit- 30 mask is superior to the two other methods in both accuracy and sensitivity. The Wilcoxon matched-pairs 31 sign rank test and paired t-Test indi
Czech name
—
Czech description
—

Type
J<sub>x</sub> - Unclassified - Peer-reviewed scientific article (Jimp, Jsc and Jost)
CEP classification
AH - Economics
OECD FORD branch
—

Publication year
2015
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Similar results(10)