Table 3 Summary of best hyperparameter configurations for each machine learning algorithm evaluated in the study: logistic regression, support vector machine, gradient Boosting, decision tree, XGBoost, and random forest. The hyperparameters were optimized to enhance classification accuracy in predicting student stress levels.

Logistic regression

penalty = [‘l1’, ‘l2’, ‘elasticnet’, ‘none’]

C = [0.001, 0.01, 0.1, 1, 10, 100]

l1_ratio = [0, 0.25, 0.5, 0.75, 1]

penalty = ‘l2’

C = 10

Support vector machine

C = [0.01, 0.1, 1, 10, 100]

kernel = [‘linear’, ‘rbf’, ‘poly’, ‘sigmoid’]

gamma = [‘scale’, ‘auto’]

degree = [2, 3, 4]

C = 10

kernel = ‘linear’

gamma = ‘scale’

Gradient boosting

n_estimators = [50, 100, 150]

learning_rate = [0.01, 0.05, 0.1, 0.2]

max_depth = [3, 5, 7]

min_samples_split = [2, 5, 10]

min_samples_leaf = [1, 2, 4]

subsample = [0.6, 0.8, 1.0]

n_estimators = 50

learning_rate = 0.01

max_depth = 7

min_samples_split = 2

min_samples_leaf = 1

subsample = 1.0

Decision tree

max_depth = [3, 5, 10, 15, 20, 25, None]

min_samples_split = [2, 5, 10, 15, 20]

min_samples_leaf = [1, 2, 4, 6, 8]

max_features = [None, ‘sqrt’, ‘log2’]

max_leaf_nodes = [None, 10, 20, 30, 40]

criterion = [‘gini’, ‘entropy’]

max_depth = 10

min_samples_split = 20

min_samples_leaf = 6

max_features = ‘sqrt’

max_leaf_nodes = None

criterion = ‘gini’

XGBoost

n_estimators = [150, 200, 250]

max_depth = [6, 8, 10]

learning_rate = [0.01, 0.05, 0.1]

subsample = [0.8, 1.0]

colsample_bytree = [0.8, 1.0]

n_estimators = 150

max_depth = 6

learning_rate = 0.05

subsample = 0.8

colsample_bytree = 1.0

Random forest

n_estimators = [150, 200, 250]

max_depth = [10, 12, 15, 18]

min_samples_split = [2, 5, 10]

min_samples_leaf = [1, 2, 3]

max_features = [‘sqrt’, ‘log2]

n_estimators = 150

max_depth = 10

min_samples_split = 10

min_samples_leaf = 1

max_features = None