Fig. 3. Model performance for four different machine learning algorithms (including Extreme gradient boosting (XGB), Decision tree (DT), Logistic regression (LR), and Support vector machine (SVM)), with default and tuned parameters settings, using the 2016–2018 dataset.

Default_LR, Default_SVM, Default_DT, and Default_XGB represent ML algorithms using default parameter settings. Tuning_LR, Tuning_SVM, Tuning_DT, and Tuning_XGB represent ML algorithms using tuned parameter settings. AUC_2016_2018 represent AUC score on 2016–2018 dataset. Recall_2016_2018 represent recall score on 2016–2018 dataset. Precision_2016_2018 represent precision score on 2016–2018 dataset. Accuracy_2016_2018 represent accuracy score on 2016–2018 dataset.