Skip to main content

Table 10 Part-D mean and standard deviation of AUPRC with varying levels of RUS (10 iterations of fivefold cross-validation)

From: Evaluating classifier performance with highly imbalanced Big Data

Class Ratio

LGB

CB-16

ET

XGB-24

RF-GPU-32

1:1

0.01567

0.01766

0.83614

0.11168

0.20205

(0.00015)

(0.00020)

(0.00307)

(0.00158)

(0.00322)

1:3

0.01724

0.02096

0.88826

0.32721

0.32806

(0.00016)

(0.00021)

(0.00181)

(0.00572)

(0.00322)

1:9

0.01910

0.02451

0.91341

0.58986

0.45801

(0.00025)

(0.00035)

(0.00103)

(0.00571)

(0.00312)

1:27

0.02095

0.02736

0.92451

0.70815

0.56448

(0.00031)

(0.00039)

(0.00080)

(0.00375)

(0.00195)

1:81

0.02203

0.02818

0.92925

0.74950

0.63787

(0.00030)

(0.00044)

(0.00073)

(0.00335)

(0.00283)

Unchanged

0.02294

0.02651

0.93288

0.76105

0.71047

(0.00037)

(0.00054)

(0.00073)

(0.00406)

(0.00169)

  1. Standard deviations are below AUPRC scores in parenthesis