Table 3.

Pseudocode of the KNN metamodel developed and investigated in this study.

PROCEDURE	K-NEAREST NEIGHBOURS
BEGIN
	Split dataset into training set and validation set
	Define k value
REPEAT
	Calculate the distance between the query point and the training points using the Euclidean distance formula
	Add the distance and the index of the training point to an ordered collection of distance subsets
	Sort the ordered collection of distance subsets and indices by the distances in ascending order
	Pick the top k distance subsets from the sorted collection
	Get the labels of the selected k subsets
	Include the mean of k labels to the prediction dataset
UNTIL	All queries in the validation dataset are calculated
RETURN	Prediction dataset
END