Forecast and Early Warning of Regional Bus Passenger Flow Based on Machine Learning

Algorithm 1

Recursive feature elimination.

	Input: training set and linear regression model
(1)	Initialization: original feature set , and feature sort set
(2)	While do
(3)	Obtain the training samples of candidate feature set
(4)	Obtain the weight of each feature by linear regression model, i.e., the coefficient of linear regression model
(5)	Find out the features of the minimum score of sorting criteria:
(6)	Update feature set
(7)	Exclude feature in S
(8)	End while
	Output: feature sort set R