Table 3. Model parameter configurations.

KNN model		Decision tree model
v1	n_neighbors = 5, metric = ‘minkowski’, p = 2	v1	max_depth = None, random_state = None
v2	n_neighbors = 5, metric = ‘minkowski’, p = 1	v2	max_depth = 25, random_state = 50
v3	n_neighbors = 5, metric = ‘minkowski’, p = 2	v3	max_depth = 50, random_state = 100
v4	n_neighbors = 10, metric= ‘minkowski’, p = 1	v4	max_depth = 75, random_state = 42
v5	n_neighbors = 10, metric = ‘minkowski’, p = 2	v5	max_depth = 100, random_state = 42
Naive bayes model		SVM model
v1	var_smoothing = 1e-8	v1	shrinking = True, random_state = None
v2	var_smoothing = 1e-8	v2	shrinking = False, random_state = 50
v3	var_smoothing = 1e-7	v3	shrinking = False, random_state = 100
v4	var_smoothing = 1e-5	v4	shrinking = False, random_state = 42
v5	var_smoothing = 1e-3	v5	shrinking = True, random_state = 42
Logistic regression model		Random forest model
v1	fit_intercept = True, random_state = None	v1	n_estimators = 100, random_state = None
v2	fit_intercept = False, random_state = 50	v2	n_estimators = 10, random_state = 50
v3	fit_intercept = False, random_state = 100	v3	n_estimators = 20, random_state = 100
v4	fit_intercept = False, random_state = 42	v4	n_estimators = 25, random_state = 42
v5	fit_intercept = False, random_state = 42	v5	n_estimators = 30, random_state = 42