Skip to main content
Journal of Big Data

Table 10 Three-factor ANOVA for F1 score

From: The effect of feature extraction and data sampling on credit card fraud detection

 

Df

Sum Sq

Mean Sq

F Value

Pr(> F)

Scenario

7

4.72

0.675

740.4

 < 2.00E-16

Classifier

3

44.8

14.934

16,383.78

 < 2.00E-16

Sampling Technique

2

3.45

1.727

1894.47

 < 2.00E-16

Scenario:Algorithm

21

17.97

0.856

938.76

 < 2.00E-16

Scenario:Sampling

14

2.92

0.208

228.49

 < 2.00E-16

Algorithm:Sampling

6

3.46

0.576

632

 < 2.00E-16

Residuals

2304

2.1

0.001

  
Back to article page