Fig 1.
Technical approach.
Fig 2.
Genetic algorithm flowchart.
Fig 3.
Stacking schematic diagram.
Table 1.
Data set presentation.
Fig 4.
Pearson correlation coefficient matrix plot.
Fig 5.
Partial results of the chi-square test.
Table 2.
Confusion matrix.
Fig 6.
Demonstration of data imbalance.
Table 3.
Performance comparison of different adoption algorithms in XGBoost model.
Table 4.
Comparison of results from various classification models.
Fig 7.
Comparison of ROC curves for various classification models.
Fig 8.
Genetic algorithm iteration data chart.
Fig 9.
The Search process of the genetic algorithm.
Table 5.
Comparison of XGBoost hyperparameter tuning optimization results.
Fig 10.
Flowchart of stacking model integration.
Fig 11.
Stacking confusion matrix.
Fig 12.
Stacking ROC curve chart.
Table 6.
Prediction results of the stacking model.
Fig 13.
Comparison chart of ROC curves for multiple models.
Table 7.
Comparison of prediction results from multiple models.
Fig 14.
SHAP of stacking.
Fig 15.
GA-XGBoost model SHAP feature density scatter plot.
Fig 16.
SHAP summary plot of feature importance ranking of GA-XGBoost model.
Fig 17.
GA-XGBoost feature importances.