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

Table 1.

The summary of the literature review.

More »

Table 1 Expand

Fig 1.

Technical route.

More »

Fig 1 Expand

Fig 2.

Genetic algorithm flow chart.

More »

Fig 2 Expand

Table 2.

Details of feature variables of the data set.

More »

Table 2 Expand

Fig 3.

Heat map of variable correlation.

More »

Fig 3 Expand

Table 3.

Chi-square test for selected features.

More »

Table 3 Expand

Table 4.

Confusion matrix.

More »

Table 4 Expand

Fig 4.

Distribution of bank customer churn label.

More »

Fig 4 Expand

Table 5.

Performance comparison of different adoption algorithms in XGBoost model.

More »

Table 5 Expand

Fig 5.

Comparison results of each classification model.

More »

Fig 5 Expand

Table 6.

Comparison results of different model.

More »

Table 6 Expand

Table 7.

Results of genetic algorithm tuning parameters.

More »

Table 7 Expand

Fig 6.

Iteration diagram of genetic algorithm.

More »

Fig 6 Expand

Fig 7.

GA-XGBoost optimization process diagram.

More »

Fig 7 Expand

Table 8.

Comparison of GA-XGBoost with XGBoost and LightGBM test results.

More »

Table 8 Expand

Fig 8.

GA-XGBoost confusion matrix.

More »

Fig 8 Expand

Fig 9.

ROC curve of GA-XGBoost.

More »

Fig 9 Expand

Fig 10.

ROC curve of models.

More »

Fig 10 Expand

Table 9.

Comparison of models test results.

More »

Table 9 Expand

Fig 11.

Summary chart of SHAP feature analysis.

More »

Fig 11 Expand

Fig 12.

SHAP summary plot of feature importance ranking of GA-XGBoost model.

More »

Fig 12 Expand

Fig 13.

GA-XGBoost feature importance order diagram.

More »

Fig 13 Expand

Fig 14.

Predicted effect of SHAP feature analysis for non-churning customers.

More »

Fig 14 Expand

Fig 15.

Effect of SHAP feature analysis for predicted churn customers.

More »

Fig 15 Expand

Fig 16.

SHAP feature dependence plot of Total_Trans_Ct and Total_Trans_Amt on model impact.

More »

Fig 16 Expand

Fig 17.

Churn prediction SHAP waterfall for the 2nd user sample.

More »

Fig 17 Expand