Electricity Theft Detection in Power Grids with Deep Learning and Random Forests

Algorithm 1

Random forest algorithm.

	Require:
	(1) Original training datasets
	(2) Test datasets
	for to do
	(1) Draw a bootstrap from the original training data
	(2) Grow an unpruned tree using data
	(a)Randomly select new feature set from original feature set
	(b)Select the best features from feature set based on Gini indicator on each node
	(c)Split until each tree grows to its maximum
	end for
	Ensure:
	(1) The collection of trees
	(2) For , the output of a decision tree is
	return