Table 1.
The summary of the literature review.
Fig 1.
Technical route.
Fig 2.
Genetic algorithm flow chart.
Table 2.
Details of feature variables of the data set.
Fig 3.
Heat map of variable correlation.
Table 3.
Chi-square test for selected features.
Table 4.
Confusion matrix.
Fig 4.
Distribution of bank customer churn label.
Table 5.
Performance comparison of different adoption algorithms in XGBoost model.
Fig 5.
Comparison results of each classification model.
Table 6.
Comparison results of different model.
Table 7.
Results of genetic algorithm tuning parameters.
Fig 6.
Iteration diagram of genetic algorithm.
Fig 7.
GA-XGBoost optimization process diagram.
Table 8.
Comparison of GA-XGBoost with XGBoost and LightGBM test results.
Fig 8.
GA-XGBoost confusion matrix.
Fig 9.
ROC curve of GA-XGBoost.
Fig 10.
ROC curve of models.
Table 9.
Comparison of models test results.
Fig 11.
Summary chart of SHAP feature analysis.
Fig 12.
SHAP summary plot of feature importance ranking of GA-XGBoost model.
Fig 13.
GA-XGBoost feature importance order diagram.
Fig 14.
Predicted effect of SHAP feature analysis for non-churning customers.
Fig 15.
Effect of SHAP feature analysis for predicted churn customers.
Fig 16.
SHAP feature dependence plot of Total_Trans_Ct and Total_Trans_Amt on model impact.
Fig 17.
Churn prediction SHAP waterfall for the 2nd user sample.