Improved classification of large imbalanced data sets using rationalized technique: Updated Class Purity Maximization Over_Sampling Technique (UCPMOT)

Journal of Big Data

Table 1 Features of data set

Category	Data set	#EX	#IR	#ATTR	#CL
Multi-class semi-structured/un-structured data sets	PAMAP2	3,850,505	14.35	54	19
	Landstat	6435	2.44	37	7
	Mashup	9135	623	8	67
	SIDO	12,678	27.04	4932	2
Multi-class structured data sets	Yeast	1484	92.6	9	10
	Car	1728	18.61	6	4
	KEGG-U	65,554	5959.45	29	43
Binary-class structured data sets	MiniBoone	130,065	2.56	51	2
	Credit card	284,808	577.87	31	2
	RLCP	5,749,132	273.67	12	2