Financial Innovation

Table 30 Discrimination performance of different feature sets

From: Clues from networks: quantifying relational risk for credit risk evaluation of SMEs

Model	Metric	BF	BF + RS	BF + CN	BF + DN	BF + SN
LR	AUC	0.717	0.727	0.723	0.731	0.726
	KS	0.410	0.420	0.416	0.435	0.419
	H	0.250	0.271	0.265	0.286	0.268
RF	AUC	0.726	0.739	0.741	0.746	0.737
	KS	0.432	0.449	0.452	0.455	0.439
	H	0.274	0.282	0.452	0.302	0.287
XGB	AUC	0.699	0.717	0.718	0.727	0.724
	KS	0.395	0.415	0.415	0.431	0.442
	H	0.228	0.253	0.253	0.248	0.260

Each metric is measured in mean of 50 estimates obtained by repeating the outer ten-fold cross-validation procedure five times

Back to article page