An Approach for Demand Forecasting in Steel Industries Using Ensemble Learning

Algorithm 4

Demand forecasting using Stacking Ensemble techniques using cross-validation.

	Input: Input dataset , where is the set of optimal hyperparameter for each based regression model, is number of based model .
	Output: final forecast demand level and performance indices.
	Step 1: learn first-level base regression models;
	/ Loop for train and evaluate the first-level individual /regressor
	for do
	Divide the dataset into and ;
	/ 70% data for training and validation, 30% for test set /
	/ Leave-One-Out Cross-Validation /
	fordo
	Train with optimal hyperparameter set on
	Predict the demand level for with
	Step 2: create a new dataset from ;
	fordo
	Create a new dataset for meta-regressor,
	Where output of model, number of based model;
	Step 3: learn second-level regressor model;
	/ Loop for train and evaluate the final-level meta-regressor model
	/fordo
	;
	Train the meta-model with using
	Predict the demand level for with
	Test set are used for the prediction and performance measure using
	return