Skip to main content

Table 17 Average MFE and MSFE loss results (30 runs)

From: Medicare fraud detection using neural networks

Method

Hidden layers

Decision threshold

ROC AUC

TPR

TNR

G-Mean

MFE-2

2

0.0350

0.8041

0.7727

0.6828

0.7249

MFE-4

4

0.0290

0.8003

0.7741

0.6727

0.7200

MSFE-2

2

0.2890

0.8065

0.7862

0.6707

0.7251

MSFE-4

4

0.2980

0.8010

0.7715

0.6847

0.7257

  1. Italic font indicates the maximum ROC AUC score