Table 1 List of HP systematically evaluated during the 10-fold cross-validation grid search analysis to find the best-performing configuration for each model.

Logistic regression (LR)

C = 0.1, 0.5, 1, 2, 5, 10

Penalty = l1, l2, elasticnet

Solver = liblinear, newton-cg, newton-cholesky

sag, saga

Support vector machine (SVM)

C = 0.1, 0.5, 1, 2, 5, 10

Kernel = linear, rbf, poly

Decision tree

Criterion = gini, entropy, log_loss

Max depth = 1, 2, 3, 4, 5, 6, 7, 8, 9, 10

Min samples leaf = 1, 2, 3, 4, 5, 6, 7, 8, 9, 10

Min samples split = 2, 3, 4, 5, 6, 7, 8, 9, 10

Random forest

Criterion = gini, entropy, log_loss

Max depth = 1, 2, 3, 4, 5, 6, 7, 8, 9, 10

Min samples leaf = 1, 2, 3, 4, 5, 6, 7, 8, 9, 10

Min samples split = 2, 3, 4, 5, 6, 7, 8, 9, 10

K-nearest neighbors

Algorithm = auto, ball_tree, kd_tree, brute

Metric = euclidean, manhattan

Num neighbors = 1, 2, 3, 4, 5, 6, 7, 8, 9, 10

Weights = uniform, distance

XGBoost

Learning rate = 0.001, 0.01, 0.1, 0.2, 0.3, 0.5

Max depth = 1, 2, 3, 4, 5, 6, 7, 8, 9, 10

Min child weight = 1, 2

Num estimators = 20, 30, 40, 50, 100, 150

Subsample = 0.1, 0.5, 1, 2, 5, 10