Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Fig 1.

Organization figure.

Structure of literature review.

More »

Fig 1 Expand

Fig 2.

Experimental procedure.

Complete experimental flow chart.

More »

Fig 2 Expand

Fig 3.

Class distributioin.

As can be seen from the graph, there is a significant imbalance in the data, with 97% majority and 3.226% minority.

More »

Fig 3 Expand

Table 1.

Anomaly records.

More »

Table 1 Expand

Fig 4.

’Equity to Liability’.

The histogram of this attribute value is skewed to some extent.

More »

Fig 4 Expand

Fig 5.

’Equity to Liability’.

A spot check of the ‘Equity to Liability’ skew value reveals that it has reached more than 7.40.

More »

Fig 5 Expand

Fig 6.

Heatmap of some variables.

Although there is a strong correlation of 0.93 between Attr1 and Attr2, 0.98 between Attr1 and Attr3, and 0.92 between Attr6 and Attr7, most of the variables have weak correlation.

More »

Fig 6 Expand

Table 2.

Binary confusion matrix.

More »

Table 2 Expand

Fig 7.

Boxplot of different models.

Among all the models, NB had the best F2-score, followed by LDA with an F2-measure of 0.333; LR, XGB, and NN had almost the same score (0.235, 0.295, and 0.304, respectively); and SVM had the lowest score, which was equal to the baseline score.

More »

Fig 7 Expand

Table 3.

F2-measure of machine learning models.

More »

Table 3 Expand

Fig 8.

Boxplot of undersampling for LDA.

All five sampling methods had similar scores; however, NCR had the lowest standard deviation.

More »

Fig 8 Expand

Table 4.

F2-measure of LDA.

More »

Table 4 Expand

Fig 9.

Boxplot of undersampling for NB.

The ENN score was the highest (0.423), the RENN score was slightly lower (0.079), and the other three undersampling scores were similar.

More »

Fig 9 Expand

Table 5.

F2-measure of NB.

More »

Table 5 Expand

Fig 10.

Boxplot of undersampling for NN.

The ENN RENN OSS shared similar highest scores; however, the standard deviation was not low, and the RENN score was 0.350.

More »

Fig 10 Expand

Fig 11.

Centroid undersampling for NB.

Without undersampling, the highest F2-score is 0.3975. Continuously increasing the undersampling rate does not blindly reduce the evaluation score. It is non-decreasing but increases when the undersampling rate is approximately 54% and 80%.

More »

Fig 11 Expand

Fig 12.

Centroid undersampling for LDA.

LDA has a higher F2-measure when the undersampling is 30%, with a value of 0.3994, and has the lowest value at 54%; it is non-decreasing but increases after 54%.

More »

Fig 12 Expand