An Approach to Data Reduction for Learning from Big Datasets: Integrating Stacking, Rotation, and Agent Population Learning Techniques

Table 1

Characteristics of the datasets used in this paper.

Dataset	Source of data	Instances	Attributes	Classes	Best reported results classification accuracy
Heart	[15]	303	13	2	90.0% [15]
Diabetes	[15]	768	8	2	77.34% [15]
WBC	[15]	699	9	2	97.5% [15]
ACredit	[15]	690	15	2	86.9% [15]
GCredit	[15]	1000	20	2	77.47% [15]
Sonar	[15]	208	60	2	97.1% [15]
Shuttle	[15]	58,000	9	7	95.6% [42]
Connect-4	[16]	67,557	42	3	—
Magic	[16]	19,020	10	2	—
Census	[16]	142,521	41	3	—