Table 1 The optimal parameter values of the model (CS).

From: Data-driven prediction on critical mechanical properties of engineered cementitious composites based on machine learning

Model

Parameter

Definition

Value

KNN

n_neighbors

Number of nearest neighbors

3

RF

n_estimators

Number of decision trees

19

max_depth

Maximum depth of each decision tree

15

max_features

Maximum number of features

8

XGB

n_estimators

Number of decision trees

64

min_child_weight

Minimum sum of instance weight

6

max_depth

Maximum depth of each decision tree

8

gamma

Minimum amount of loss required for further branching

0.3