Leveraging augmentation techniques for tasks with unbalancedness within the financial domain: a two-level ensemble approach

EPJ Data Science

Table 10 Details about the bankruptcy in Poland dataset

# Groups	# Training samples	#Candidates for test set	# Test set in each run	K value
First	13,412	542	100	5
Second	19,446	800	100	8
Third	19,916	990	100	9
Forth	18,454	1030	100	10
Fifth	10,900	820	100	8