Neighborhood rough set and SVM based hybrid credit scoring classifier

A hybrid data mining model of feature selection algorithms and ensemble learning classifiers for credit scoring

“…Zhou et al (2009) used direct search for parameters selection in the SVM classification algorithm. In a study by Ping and Yongheng (2011), neighborhood rough set and the SVM-based classifier were used for credit scoring. In another study (Kao et al, 2012), Bayesian latent variable model with classification regression tree was employed.…”

Advances in credit scoring: combining performance and interpretation in kernel discriminant analysis

“…We have to underline that, most of the times, qualitative information is not treated properly: in Akkoç (2012) and Ping and Yongheng (2011) categorical predictors are employed as numerical ones. Alternatively, they were encoded as binary features using 1-of-k encoding (Gönen et al 2012;Abdou et al 2008), but such process generally generates a matrix with linearly dependent columns that produces non-robust estimates.…”

Eficiencia de los modelos Poisson y Logístico en la asignación de probabilidades de incumplimiento a empresas mineras mexicanas

“…Entre los modelos no probabilistas usados en la literatura para calcular dichas probabilidades, también se encuentran los propuestos por (Huang, Chen, & Wang, 2007) quienes construyen modelos de calificación de crédito basado en Support Vector Machines (SVM) híbridos, para evaluar la puntuación de crédito de solicitantes de tarjetas de crédito, por su parte, (Ping & Yongheng, 2011) hacen un esfuerzo similar, el que comparan con modelos de análisis discriminante lineal, regresión logística y redes neuronales.…”