Journal of Big Data

Table 7 German Dataset

From: A machine learning-based credit risk prediction engine system using a stacked classifier and a filter-based feature selection method

Model	Accuracy	F1-Score	AUC
RF	75.20%	47.45%	0.644
GB	72.40%	37.83%	0.595
XGB	74.01%	48.81%	0.647
KNN	68.40%	48.82%	0.547
ANN	74.80%	45.21%	0.633
DT	73.60%	47.61%	0.640
Stacked (Proposed)	82.80%	86.35%	0.944

Back to article page