Table 3 Best hyper parameters selected for machine learning algorithms

XGB

‘min_chid_weigh’ = 4’max_depht’ = 12,’learning_rate’ = 0.4, ‘gamma’ = 0.6, ‘colsample_bytree’ = 0.9

0.88

K-NN

(leaf_size = list(range(1,20)), n_neighbors = list(range(1,9)), p = [1, 2])

0.73

AdaBoost

(“random_state”: 924, “n_estimators”: 92, “learning rate”: 0.4, “algorithm”: “samme.R”)

0.89

HGB

(‘verbose’ = 4, ‘random_state’ = 84, ‘max_leaf_nodes’ = 78, ‘max_iter’ = 180, ‘max_depht’ = 11, ‘learning rate’ = 0.8)

0.94