Prediction of Labor Unemployment Based on Time Series Model and Neural Network Model

Algorithm 1

Process of learning of network.

(1)	Initialize the neural network weights;
(2)	Input P training samples in turn, and assuming that the currently inputted learning sample is the p-th training sample;
(3)	Calculate the output sequentially;
(4)	Solve the back propagation error;
(5)	Record the number that has been examined. If p < P, turn to (2), if p = P, continue to (6);
(6)	Revise the correction formula of the weight value of each layer or the right;
(7)	Recalculate the output of the hidden layer according to the new weight or core value, and if the maximum learning times are reached for each p and P, end the network learning.