An Empirical Study on the Performance of Cost-Sensitive Boosting Algorithms with Different Levels of Class Imbalance

Table 3

Index of performance using 𝐹-measure for severely imbalanced data sets.

	Win	Loss	Index	Win	Loss	Index	Win	Loss	Index	Win	Loss	Index	Win	Loss	Index
	0.1			0.2			0.3			0.4			0.5
AdaC1	19	0	19	13	0	13	10	0	10	12	0	12	13	0	13
AdaC2	6	7	−1	8	5	3	12	3	9	13	2	11	16	2	14
AdaC3	1	12	−11	1	6	−5	7	5	2	9	5	4	10	4	6
AdaCost	1	4	−3	0	7	−7	0	15	−15	0	21	−21	0	25	−25
CSB1	2	2	0	2	3	−1	0	5	−1	0	5	−5	0	5	−5
CSB2	0	4	−4	0	3	−3	0	1	−4	0	1	−1	0	3	−3
	0.6			0.7			0.8			0.9			1
AdaC1	12	0	12	13	0	13	10	0	10	12	0	12	14	0	14
AdaC2	18	1	17	17	1	16	17	0	17	15	0	15	14	0	14
AdaC3	11	4	7	9	5	4	11	3	8	14	1	13	13	0	13
AdaCost	0	26	−26	0	27	−27	0	27	−27	0	27	−27	1	27	−26
CSB1	0	7	−7	0	5	−5	0	8	−8	1	10	−9	0	15	−15
CSB2	0	3	−3	0	1	−1	0	0	0	0	4	−4	0	0	0